Clarify release automation proposal

chore: add change proposals for agent scaffolding (#108 )
chore: release 0.7.0 (#107 )
2026-10-04 06:18:24 +08:00 · 2025-10-02 00:54:14 +10:00 · 2025-10-02 00:26:25 +10:00 · 2025-10-01 23:01:23 +10:00 · 2025-10-01 22:51:15 +10:00 · 2025-10-01 19:01:10 +10:00
102 changed files with 2346 additions and 755 deletions
@@ -15,10 +15,12 @@ concurrency:
  cancel-in-progress: true

 jobs:
-  test:
+  test_pr:
    name: Test
    runs-on: ubuntu-latest
-    
+    timeout-minutes: 10
+    if: github.event_name == 'pull_request'
+
    steps:
      - name: Checkout code
        uses: actions/checkout@v4
@@ -48,7 +50,68 @@ jobs:
      - name: Upload test coverage
        uses: actions/upload-artifact@v4
        with:
-          name: coverage-report
+          name: coverage-report-pr
+          path: coverage/
+          retention-days: 7
+
+  test_matrix:
+    name: Test (${{ matrix.label }})
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15
+    if: github.event_name != 'pull_request'
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: ubuntu-latest
+            shell: bash
+            label: linux-bash
+          - os: macos-latest
+            shell: bash
+            label: macos-bash
+          - os: windows-latest
+            shell: pwsh
+            label: windows-pwsh
+
+    defaults:
+      run:
+        shell: ${{ matrix.shell }}
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '20'
+          cache: 'pnpm'
+
+      - name: Print environment diagnostics
+        run: |
+          node -p "JSON.stringify({ platform: process.platform, arch: process.arch, shell: process.env.SHELL || process.env.ComSpec || '' })"
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Build project
+        run: pnpm run build
+
+      - name: Run tests
+        run: pnpm test
+
+      - name: Upload test coverage
+        if: matrix.os == 'ubuntu-latest'
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-report-main
          path: coverage/
          retention-days: 7

@@ -122,15 +185,15 @@ jobs:
            echo "Changesets not configured, skipping validation"
          fi

-  required-checks:
+  required-checks-pr:
    name: All checks passed
    runs-on: ubuntu-latest
-    needs: [test, lint]
-    if: always()
+    needs: [test_pr, lint]
+    if: always() && github.event_name == 'pull_request'
    steps:
      - name: Verify all checks passed
        run: |
-          if [[ "${{ needs.test.result }}" != "success" ]]; then
+          if [[ "${{ needs.test_pr.result }}" != "success" ]]; then
            echo "Test job failed"
            exit 1
          fi
@@ -138,4 +201,22 @@ jobs:
            echo "Lint job failed"
            exit 1
          fi
-          echo "All required checks passed!"
+          echo "All required checks passed!"
+
+  required-checks-main:
+    name: All checks passed
+    runs-on: ubuntu-latest
+    needs: [test_matrix, lint]
+    if: always() && github.event_name != 'pull_request'
+    steps:
+      - name: Verify all checks passed
+        run: |
+          if [[ "${{ needs.test_matrix.result }}" != "success" ]]; then
+            echo "Matrix test job failed"
+            exit 1
+          fi
+          if [[ "${{ needs.lint.result }}" != "success" ]]; then
+            echo "Lint job failed"
+            exit 1
+          fi
+          echo "All required checks passed!"
@@ -1,40 +1,8 @@
 <!-- OPENSPEC:START -->
-# OpenSpec Project
+# OpenSpec Instructions

-This document provides instructions for AI coding assistants on how to use OpenSpec conventions for spec-driven development. Follow these rules precisely when working on OpenSpec-enabled projects.
+This project uses OpenSpec to manage AI assistant workflows.

-This project uses OpenSpec for spec-driven development. Specifications are the source of truth.
-
-See @openspec/AGENTS.md for detailed conventions and guidelines.
+- Full guidance lives in '@/openspec/AGENTS.md'.
+- Keep this managed block so 'openspec update' can refresh the instructions.
 <!-- OPENSPEC:END -->
-
-## Complexity Management
-
-**Default to minimal solutions:**
- Propose <100 lines of new code for features
- Prefer single-file implementations until proven insufficient
- Avoid frameworks, abstractions, and optimizations without clear justification
- Choose boring, well-understood patterns over novel approaches
-
-**Question requests for complexity:**
- Caching? → Ask for performance data and targets
- New framework? → Suggest plain code first
- Extra layers? → Start with the thinnest viable design
-
-**Justify complexity with data:**
- Performance metrics showing current solution is too slow
- Concrete scale requirements (e.g., >1000 users, >100MB data)
- Multiple proven use cases requiring an abstraction
-
-## Package Manager
-Always use pnpm (NOT npm or yarn) for all Node.js package management:
- Install dependencies: `pnpm install`
- Add packages: `pnpm add [package]`
- Run scripts: `pnpm run [script]`
-
-## Git Commits
-Use conventional commits with these rules:
- Format: `type(scope): subject` (e.g., `fix: resolve auth error`, `feat(api): add user endpoint`)
- Keep commit messages to ONE line only - no body or footer
- Common types: feat, fix, docs, style, refactor, test, chore
- Never add co-authorship lines or attribution
@@ -1,5 +1,54 @@
 # @fission-ai/openspec

+## 0.7.0
+
+### Minor Changes
+
+- Add native Kilo Code workflow integration so `openspec init` and `openspec update` manage `.kilocode/workflows/openspec-*.md` files.
+- Always scaffold the managed root `AGENTS.md` hand-off stub and regroup the AI tool prompts during init/update to keep instructions consistent.
+
+## 0.6.0
+
+### Minor Changes
+
+- Slim the generated root agent instructions down to a managed hand-off stub and update the init/update flows to refresh it safely.
+
+## 0.5.0
+
+### Minor Changes
+
+- feat: implement Phase 1 E2E testing with cross-platform CI matrix
+
+  - Add shared runCLI helper in test/helpers/run-cli.ts for spawn testing
+  - Create test/cli-e2e/basic.test.ts covering help, version, validate flows
+  - Migrate existing CLI exec tests to use runCLI helper
+  - Extend CI matrix to bash (Linux/macOS) and pwsh (Windows)
+  - Split PR and main workflows for optimized feedback
+
+### Patch Changes
+
+- Make apply instructions more specific
+
+  Improve agent templates and slash command templates with more specific and actionable apply instructions.
+
+- docs: improve documentation and cleanup
+
+  - Document non-interactive flag for archive command
+  - Replace discord badge in README
+  - Archive completed changes for better organization
+
+## 0.4.0
+
+### Minor Changes
+
+- Add OpenSpec change proposals for CLI improvements and enhanced user experience
+- Add Opencode slash commands support for AI-driven development workflows
+
+### Patch Changes
+
+- Add documentation improvements including --yes flag for archive command template and Discord badge
+- Fix normalize line endings in markdown parser to handle CRLF files properly
+
 ## 0.3.0

 ### Minor Changes
@@ -15,7 +15,7 @@
  <a href="https://nodejs.org/"><img alt="node version" src="https://img.shields.io/node/v/@fission-ai/openspec?style=flat-square" /></a>
  <a href="./LICENSE"><img alt="License: MIT" src="https://img.shields.io/badge/License-MIT-blue.svg?style=flat-square" /></a>
  <a href="https://conventionalcommits.org"><img alt="Conventional Commits" src="https://img.shields.io/badge/Conventional%20Commits-1.0.0-yellow.svg?style=flat-square" /></a>
-  <a href="https://discord.gg/saTQQGQZ"><img alt="Discord" src="https://img.shields.io/discord/1411657095639601154?logo=discord&logoColor=white&style=flat-square" /></a>
+  <a href="https://discord.gg/saTQQGQZ"><img alt="Discord" src="https://img.shields.io/badge/Discord-Join%20the%20community-5865F2?logo=discord&logoColor=white&style=flat-square" /></a>
 </p>

 <p align="center">
@@ -83,13 +83,17 @@ These tools have built-in OpenSpec commands. Select the OpenSpec integration whe
 |------|----------|
 | **Claude Code** | `/openspec:proposal`, `/openspec:apply`, `/openspec:archive` |
 | **Cursor** | `/openspec-proposal`, `/openspec-apply`, `/openspec-archive` |
+| **OpenCode** | `/openspec-proposal`, `/openspec-apply`, `/openspec-archive` |
+| **Kilo Code** | `/openspec-proposal.md`, `/openspec-apply.md`, `/openspec-archive.md` (`.kilocode/workflows/`) |
+
+Kilo Code discovers team workflows automatically. Save the generated files under `.kilocode/workflows/` and trigger them from the command palette with `/openspec-proposal.md`, `/openspec-apply.md`, or `/openspec-archive.md`.

 #### AGENTS.md Compatible
 These tools automatically read workflow instructions from `openspec/AGENTS.md`. Ask them to follow the OpenSpec workflow if they need a reminder. Learn more about the [AGENTS.md convention](https://agents.md/).

 | Tools |
 |-------|
-| Codex • Amp • Jules • OpenCode • Gemini CLI • GitHub Copilot • Others |
+| Codex • Amp • Jules • Gemini CLI • GitHub Copilot • Others |

 ### Install & Initialize

@@ -120,8 +124,8 @@ openspec init
 ```

 **What happens during initialization:**
- You'll be prompted to select your AI tool (Claude Code, Cursor, etc.)
- OpenSpec automatically configures slash commands or `AGENTS.md` based on your selection
+- You'll be prompted to pick any natively supported AI tools (Claude Code, Cursor, OpenCode, etc.); other assistants always rely on the shared `AGENTS.md` stub
+- OpenSpec automatically configures slash commands for the tools you choose and always writes a managed `AGENTS.md` hand-off at the project root
 - A new `openspec/` directory structure is created in your project

 **After setup:**
@@ -184,13 +188,13 @@ You: Please archive the change
     (Shortcut for tools with slash commands: /openspec:archive add-profile-filters)

 AI:  I'll archive the add-profile-filters change.
-     *Runs: openspec archive add-profile-filters*
+    *Runs: openspec archive add-profile-filters --yes*
     ✓ Change archived successfully. Specs updated. Ready for the next feature!
 ```

 Or run the command yourself in terminal:
 ```bash
-$ openspec archive add-profile-filters  # Archive the completed change
+$ openspec archive add-profile-filters --yes  # Archive the completed change without prompts
 ```

 **Note:** Tools with native slash commands (Claude Code, Cursor) can use the shortcuts shown. All other tools work with natural language requests to "create an OpenSpec proposal", "apply the OpenSpec change", or "archive the change".
@@ -202,7 +206,7 @@ openspec list               # View active change folders
 openspec view               # Interactive dashboard of specs and changes
 openspec show <change>      # Display change details (proposal, tasks, spec updates)
 openspec validate <change>  # Check spec formatting and structure
-openspec archive <change>   # Move a completed change into archive/
+openspec archive <change> [--yes|-y]   # Move a completed change into archive/ (non-interactive with --yes)
 ```

 ## Example: How AI Creates OpenSpec Files
@@ -1,7 +1,15 @@
 #!/usr/bin/env node

-import { execSync } from 'child_process';
+import { execFileSync } from 'child_process';
 import { existsSync, rmSync } from 'fs';
+import { createRequire } from 'module';
+
+const require = createRequire(import.meta.url);
+
+const runTsc = (args = []) => {
+  const tscPath = require.resolve('typescript/bin/tsc');
+  execFileSync(process.execPath, [tscPath, ...args], { stdio: 'inherit' });
+};

 console.log('🔨 Building OpenSpec...\n');

@@ -14,10 +22,10 @@ if (existsSync('dist')) {
 // Run TypeScript compiler (use local version explicitly)
 console.log('Compiling TypeScript...');
 try {
-  execSync('./node_modules/.bin/tsc -v', { stdio: 'inherit' });
-  execSync('./node_modules/.bin/tsc', { stdio: 'inherit' });
+  runTsc(['--version']);
+  runTsc();
  console.log('\n✅ Build completed successfully!');
 } catch (error) {
  console.error('\n❌ Build failed!');
  process.exit(1);
-}
+}
@@ -47,18 +47,20 @@ Skip proposal for:
 4. Run `openspec validate <id> --strict` and resolve any issues before sharing the proposal.

 ### Stage 2: Implementing Changes
+Track these steps as TODOs and complete them one by one.
 1. **Read proposal.md** - Understand what's being built
 2. **Read design.md** (if exists) - Review technical decisions
 3. **Read tasks.md** - Get implementation checklist
 4. **Implement tasks sequentially** - Complete in order
-5. **Mark complete immediately** - Update `- [x]` after each task
-6. **Approval gate** - Do not start implementation until the proposal is reviewed and approved
+5. **Confirm completion** - Ensure every item in `tasks.md` is finished before updating statuses
+6. **Update checklist** - After all work is done, set every task to `- [x]` so the list reflects reality
+7. **Approval gate** - Do not start implementation until the proposal is reviewed and approved

 ### Stage 3: Archiving Changes
 After deployment, create separate PR to:
 - Move `changes/[name]/` → `changes/archive/YYYY-MM-DD-[name]/`
 - Update `specs/` if capabilities changed
- Use `openspec archive [change] --skip-specs` for tooling-only changes
+- Use `openspec archive [change] --skip-specs --yes` for tooling-only changes
 - Run `openspec validate --strict` to confirm the archived change passes checks

 ## Before Any Task
@@ -95,7 +97,7 @@ openspec list --specs          # List specifications
 openspec show [item]           # Display change or spec
 openspec diff [change]         # Show spec differences
 openspec validate [item]       # Validate changes or specs
-openspec archive [change]      # Archive after deployment
+openspec archive [change] [--yes|-y]      # Archive after deployment (add --yes for non-interactive runs)

 # Project management
 openspec init [path]           # Initialize OpenSpec
@@ -117,6 +119,7 @@ openspec validate [change] --strict
 - `--strict` - Comprehensive validation
 - `--no-interactive` - Disable prompts
 - `--skip-specs` - Archive without spec updates
+- `--yes`/`-y` - Skip confirmation prompts (non-interactive archive)

 ## Directory Structure

@@ -447,7 +450,7 @@ openspec list              # What's in progress?
 openspec show [item]       # View details
 openspec diff [change]     # What's changing?
 openspec validate --strict # Is it correct?
-openspec archive [change]  # Mark complete
+openspec archive [change] [--yes|-y]  # Mark complete (add --yes for automation)
 ```

 Remember: Specs are truth. Changes are proposals. Keep them in sync.
@@ -0,0 +1,17 @@
+## Why
+- Kilo Code executes \"slash commands\" by loading markdown workflows from `.kilocode/workflows/` (or the global `~/.kilocode/workflows/`) and running them when a user types `/workflow-name.md`, making project-local workflow files the analogue to the slash-command files we already ship for other tools.\\
+  ([Workflows | Kilo Code Docs](https://kilocode.ai/docs/features/slash-commands/workflows))
+- Those workflows are plain markdown with step-by-step instructions that can call built-in tools and MCP integrations, so reusing OpenSpec's shared proposal/apply/archive bodies keeps behaviour aligned across assistants without inventing new content.
+- OpenSpec already detects configured tools and refreshes marker-wrapped files during `init`/`update`; extending the same mechanism to `.kilocode/workflows/openspec-*.md` ensures Kilo Code stays in sync with one source of truth.
+
+## What Changes
+- Add Kilo Code to the `openspec init` tool picker with \"already configured\" detection, including wiring for extend mode so teams can refresh Kilo Code assets.
+- Implement a `KiloCodeSlashCommandConfigurator` that creates `.kilocode/workflows/openspec-{proposal,apply,archive}.md`, ensuring the workflow directory exists and wrapping shared content in OpenSpec markers (no front matter required).
+- Teach `openspec update` to refresh existing Kilo Code workflows (and only those that already exist) using the shared slash-command templates.
+- Update documentation, release notes, and integration tests so the new workflow support is covered alongside Claude, Cursor, OpenCode, and Windsurf.
+
+## Impact
+- Specs: `cli-init`, `cli-update`
+- Code: `src/core/config.ts`, `src/core/configurators/(registry|slash/*)`, `src/core/templates/slash-command-templates.ts`, CLI wiring for tool summaries
+- Tests: init/update workflow coverage, regression for marker preservation in `.kilocode/workflows/`
+- Docs: README / CHANGELOG updates advertising Kilo Code workflow support
@@ -0,0 +1,24 @@
+## MODIFIED Requirements
+### Requirement: AI Tool Configuration
+The command SHALL configure AI coding assistants with OpenSpec instructions using a marker system.
+#### Scenario: Prompting for AI tool selection
+- **WHEN** run interactively
+- **THEN** prompt the user with "Which AI tools do you use?" using a multi-select menu
+- **AND** list every available tool with a checkbox:
+  - Claude Code (creates or refreshes CLAUDE.md and slash commands)
+  - Cursor (creates or refreshes `.cursor/commands/*` slash commands)
+  - OpenCode (creates or refreshes `.opencode/command/openspec-*.md` slash commands)
+  - Windsurf (creates or refreshes `.windsurf/workflows/openspec-*.md` workflows)
+  - Kilo Code (creates or refreshes `.kilocode/workflows/openspec-*.md` workflows)
+  - AGENTS.md standard (creates or refreshes AGENTS.md with OpenSpec markers)
+- **AND** show "(already configured)" beside tools whose managed files exist so users understand selections will refresh content
+- **AND** treat disabled tools as "coming soon" and keep them unselectable
+- **AND** allow confirming with Enter after selecting one or more tools
+
+### Requirement: Slash Command Configuration
+The init command SHALL generate slash command files for supported editors using shared templates.
+#### Scenario: Generating slash commands for Kilo Code
+- **WHEN** the user selects Kilo Code during initialization
+- **THEN** create `.kilocode/workflows/openspec-proposal.md`, `.kilocode/workflows/openspec-apply.md`, and `.kilocode/workflows/openspec-archive.md`
+- **AND** populate each file from shared templates (wrapped in OpenSpec markers) so workflow text matches other tools
+- **AND** each template includes instructions for the relevant OpenSpec workflow stage
@@ -0,0 +1,8 @@
+## MODIFIED Requirements
+### Requirement: Slash Command Updates
+The update command SHALL refresh existing slash command files for configured tools without creating new ones.
+#### Scenario: Updating slash commands for Kilo Code
+- **WHEN** `.kilocode/workflows/` contains `openspec-proposal.md`, `openspec-apply.md`, and `openspec-archive.md`
+- **THEN** refresh each file using shared templates wrapped in OpenSpec markers
+- **AND** ensure templates include instructions for the relevant workflow stage
+- **AND** skip creating missing files (the update command only refreshes what already exists)
@@ -0,0 +1,15 @@
+## 1. CLI wiring
+- [x] 1.1 Add Kilo Code to the selectable AI tools in `openspec init`, including "already configured" detection and success summaries.
+- [x] 1.2 Register a `KiloCodeSlashCommandConfigurator` alongside other slash-command tools.
+
+## 2. Workflow generation
+- [x] 2.1 Implement the configurator so it creates `.kilocode/workflows/` (if needed) and writes `openspec-{proposal,apply,archive}.md` with OpenSpec markers.
+- [x] 2.2 Reuse the shared slash-command bodies without front matter; verify resulting files stay Markdown-only with no extra metadata.
+
+## 3. Update support
+- [x] 3.1 Ensure `openspec update` refreshes existing Kilo Code workflows while skipping ones that are absent.
+- [x] 3.2 Add regression coverage confirming marker content is replaced (not duplicated) during updates.
+
+## 4. Documentation
+- [x] 4.1 Update README / docs to note Kilo Code workflow support and path (`.kilocode/workflows/`).
+- [x] 4.2 Mention the integration in CHANGELOG or release notes if applicable.
@@ -0,0 +1,11 @@
+## Why
+Manual setup for new changes leads to formatting mistakes in spec deltas and slows agents who must recreate the same file skeletons for every proposal. A built-in scaffold command will generate compliant templates so assistants can focus on the change content instead of structure.
+
+## What Changes
+- Add an `openspec scaffold <change-id>` CLI command that creates a change directory with validated `proposal.md`, `tasks.md`, and spec delta templates.
+- Update CLI documentation and quick-reference guidance so agents discover the scaffold workflow before drafting files manually.
+- Add automated coverage (unit/integ tests) to ensure the command respects existing naming rules and generated Markdown passes validation.
+
+## Impact
+- Affected specs: `specs/cli-scaffold`
+- Affected code: `src/cli/index.ts`, `src/commands`, `docs/`
@@ -0,0 +1,44 @@
+## ADDED Requirements
+### Requirement: Scaffolding Command Registration
+The CLI SHALL expose an `openspec scaffold <change-id>` command that validates the change identifier before generating files.
+
+#### Scenario: Registering scaffold command
+- **WHEN** a user runs `openspec scaffold add-user-notifications`
+- **THEN** the CLI SHALL reject invalid identifiers (non kebab-case) before proceeding
+- **AND** display usage documentation via `openspec scaffold --help`
+- **AND** exit with code 0 after successful scaffolding
+
+### Requirement: Change Directory Structure
+The scaffold command SHALL create the standard change workspace with proposal, tasks, optional design, and delta directories laid out according to OpenSpec conventions.
+
+#### Scenario: Generating change workspace
+- **WHEN** scaffolding a new change with id `add-user-notifications`
+- **THEN** create `openspec/changes/add-user-notifications/`
+- **AND** generate `proposal.md`, `tasks.md`, and `design.md` (commented placeholder content) in that directory when missing
+- **AND** create `openspec/changes/add-user-notifications/specs/` ready for capability-specific deltas
+
+### Requirement: Template Content Guidance
+The scaffold command SHALL populate generated Markdown files with OpenSpec-compliant templates so authors can copy, edit, and pass validation without reformatting.
+
+#### Scenario: Populating proposal and tasks templates
+- **WHEN** the scaffold command writes `proposal.md`
+- **THEN** include the `## Why`, `## What Changes`, and `## Impact` headings with placeholder guidance text
+- **AND** ensure `tasks.md` starts with `## 1. Implementation` and numbered checklist items using `- [ ]` syntax
+- **AND** annotate optional sections (like `design.md`) with inline TODO comments so users understand when to keep or delete them
+
+### Requirement: Delta Spec Creation
+The scaffold command SHALL create at least one capability delta file with correctly formatted requirement and scenario placeholders that guide authors to enter the actual behavior.
+
+#### Scenario: Creating spec delta skeleton
+- **WHEN** scaffolding a change and the capability `cli-scaffold` is provided interactively or via flags
+- **THEN** generate `openspec/changes/add-user-notifications/specs/cli-scaffold/spec.md`
+- **AND** include `## ADDED Requirements` with at least one `### Requirement:` block and matching `#### Scenario:` entries that remind the author to replace placeholder text
+- **AND** ensure the generated delta passes `openspec validate add-user-notifications --strict` until the author edits it
+
+### Requirement: Idempotent Execution
+The scaffold command SHALL be safe to rerun, preserving user edits while filling in any missing managed sections.
+
+#### Scenario: Rerunning scaffold on existing change
+- **WHEN** the command is executed again for an existing change directory containing user-edited files
+- **THEN** leave existing content untouched except for managed placeholder regions or missing files that need creation
+- **AND** update the filesystem summary to highlight which files were skipped, created, or refreshed
@@ -0,0 +1,11 @@
+## 1. CLI scaffolding command
+- [ ] 1.1 Register an `openspec scaffold` command in the CLI entrypoint with `change-id` argument validation.
+- [ ] 1.2 Implement generator logic that creates the change directory structure plus default `proposal.md`, `tasks.md`, and delta spec skeletons without overwriting existing populated files.
+
+## 2. Templates and documentation
+- [ ] 2.1 Surface copy/paste templates and scaffold usage in the top-level quick reference for `openspec/AGENTS.md`.
+- [ ] 2.2 Refresh other CLI docs (`docs/`, README) to mention the scaffold workflow and link to instructions.
+
+## 3. Test coverage
+- [ ] 3.1 Add unit tests covering name validation, file generation, and idempotent reruns.
+- [ ] 3.2 Add integration coverage ensuring generated files pass `openspec validate --strict` without manual edits.
@@ -0,0 +1,17 @@
+## Why
+- Windsurf exposes "Workflows" as the vehicle for slash-like automation: saved Markdown files under `.windsurf/workflows/` that Cascade discovers across the workspace (including subdirectories and up to the git root), then executes when a user types `/workflow-name`. These files can be team-authored, must stay under 12k characters, and can call other workflows, making them the natural place to publish OpenSpec guidance for Windsurf users.\
+  ([Windsurf Workflows documentation](https://docs.windsurf.com/windsurf/cascade/workflows))
+- The Wave 12 changelog reiterates that workflows are invoked via slash commands and that Windsurf stores them in `.windsurf/workflows`, so the OpenSpec CLI just needs to generate Markdown there to participate in Windsurf's command palette.\
+  ("Custom Workflows" section, [Windsurf changelog](https://windsurf.com/changelog))
+- OpenSpec already ships shared command bodies for proposal/apply/archive and uses markers so commands stay up to date. Extending the same templates to Windsurf keeps behaviour consistent with Claude, Cursor, and OpenCode without inventing new content flows.
+
+## What Changes
+- Add Windsurf to the CLI tool picker (`openspec init`) and the slash-command registry so selecting it scaffolds `.windsurf/workflows/openspec-proposal.md`, `openspec-apply.md`, and `openspec-archive.md` with marker-managed bodies.
+- Shape each Windsurf workflow with a short heading/description plus the existing OpenSpec guardrails/steps wrapped in markers, ensuring the total payload remains well below the 12,000 character limit.
+- Ensure `openspec update` refreshes existing Windsurf workflows (and only those that already exist) in-place, mirroring current behaviour for other editors.
+- Extend unit tests for init/update to cover Windsurf generation and updates, and update the README/tooling docs to advertise Windsurf support.
+
+## Impact
+- Specs: `cli-init`, `cli-update`
+- Code: `src/core/configurators/slash/*`, `src/core/templates/slash-command-templates.ts`, CLI prompts, README
+- Tests: init/update integration coverage for Windsurf workflows
@@ -0,0 +1,23 @@
+## MODIFIED Requirements
+### Requirement: AI Tool Configuration
+The command SHALL configure AI coding assistants with OpenSpec instructions using a marker system.
+#### Scenario: Prompting for AI tool selection
+- **WHEN** run interactively
+- **THEN** prompt the user with "Which AI tools do you use?" using a multi-select menu
+- **AND** list every available tool with a checkbox:
+  - Claude Code (creates or refreshes CLAUDE.md and slash commands)
+  - Cursor (creates or refreshes `.cursor/commands/*` slash commands)
+  - OpenCode (creates or refreshes `.opencode/command/openspec-*.md` slash commands)
+  - Windsurf (creates or refreshes `.windsurf/workflows/openspec-*.md` workflows)
+  - AGENTS.md standard (creates or refreshes AGENTS.md with OpenSpec markers)
+- **AND** show "(already configured)" beside tools whose managed files exist so users understand selections will refresh content
+- **AND** treat disabled tools as "coming soon" and keep them unselectable
+- **AND** allow confirming with Enter after selecting one or more tools
+
+### Requirement: Slash Command Configuration
+The init command SHALL generate slash command files for supported editors using shared templates.
+#### Scenario: Generating slash commands for Windsurf
+- **WHEN** the user selects Windsurf during initialization
+- **THEN** create `.windsurf/workflows/openspec-proposal.md`, `.windsurf/workflows/openspec-apply.md`, and `.windsurf/workflows/openspec-archive.md`
+- **AND** populate each file from shared templates (wrapped in OpenSpec markers) so workflow text matches other tools
+- **AND** each template includes instructions for the relevant OpenSpec workflow stage
@@ -0,0 +1,8 @@
+## MODIFIED Requirements
+### Requirement: Slash Command Updates
+The update command SHALL refresh existing slash command files for configured tools without creating new ones.
+#### Scenario: Updating slash commands for Windsurf
+- **WHEN** `.windsurf/workflows/` contains `openspec-proposal.md`, `openspec-apply.md`, and `openspec-archive.md`
+- **THEN** refresh each file using shared templates wrapped in OpenSpec markers
+- **AND** ensure templates include instructions for the relevant workflow stage
+- **AND** skip creating missing files (the update command only refreshes what already exists)
@@ -0,0 +1,17 @@
+## 1. CLI wiring
+- [ ] 1.1 Add Windsurf to the selectable AI tools in `openspec init`, including "already configured" detection.
+- [ ] 1.2 Register a `WindsurfSlashCommandConfigurator` that writes workflows to `.windsurf/workflows/` and ensures the directory exists.
+- [ ] 1.3 Ensure `openspec update` pulls the Windsurf configurator when winds is selected and skips creation when files are absent.
+
+## 2. Workflow templates
+- [ ] 2.1 Reuse the shared proposal/apply/archive bodies, adding Windsurf-specific headings/description before the OpenSpec markers.
+- [ ] 2.2 Confirm generated Markdown (per file) stays comfortably under the 12k character ceiling noted in the Windsurf docs.
+
+## 3. Tests & safeguards
+- [ ] 3.1 Extend init tests to assert creation of `.windsurf/workflows/openspec-*.md` when Windsurf is chosen.
+- [ ] 3.2 Extend update tests to assert existing Windsurf workflows are refreshed and non-existent files are ignored.
+- [ ] 3.3 Add regression coverage for marker preservation inside Windsurf workflow files.
+
+## 4. Documentation
+- [ ] 4.1 Update README (and any user-facing docs) to list Windsurf under native slash/workflow integrations.
+- [ ] 4.2 Call out Windsurf workflow support in release notes or CHANGELOG if applicable.
@@ -13,3 +13,9 @@ The init command SHALL generate slash command files for supported editors using
 - **THEN** create `.cursor/commands/openspec-proposal.md`, `.cursor/commands/openspec-apply.md`, and `.cursor/commands/openspec-archive.md`
 - **AND** populate each file from shared templates so command text matches other tools
 - **AND** each template includes instructions for the relevant OpenSpec workflow stage
+
+#### Scenario: Generating slash commands for OpenCode
+- **WHEN** the user selects OpenCode during initialization
+- **THEN** create `.opencode/commands/openspec-proposal.md`, `.opencode/commands/openspec-apply.md`, and `.opencode/commands/openspec-archive.md`
+- **AND** populate each file from shared templates so command text matches other tools
+- **AND** each template includes instructions for the relevant OpenSpec workflow stage
@@ -12,6 +12,11 @@ The update command SHALL refresh existing slash command files for configured too
 - **THEN** refresh each file using shared templates
 - **AND** ensure templates include instructions for the relevant workflow stage

+#### Scenario: Updating slash commands for OpenCode
+- **WHEN** `.opencode/commands/` contains `openspec-proposal.md`, `openspec-apply.md`, and `openspec-archive.md`
+- **THEN** refresh each file using shared templates
+- **AND** ensure templates include instructions for the relevant workflow stage
+
 #### Scenario: Missing slash command file
 - **WHEN** a tool lacks a slash command file
 - **THEN** do not create a new file during update
@@ -14,3 +14,7 @@

 ## 4. Verification
 - [x] 4.1 Add tests verifying slash command files are created and updated correctly.
+
+## 5. OpenCode Integration
+- [x] 5.1 Generate `.opencode/commands/{openspec-proposal,openspec-apply,openspec-archive}.md` during `openspec init` using shared templates.
+- [x] 5.2 Update existing `.opencode/commands/*` files during `openspec update`.
@@ -0,0 +1,19 @@
+## Why
+Recent cross-shell regressions for `openspec` commands revealed that our existing unit/integration tests do not exercise the packaged CLI or shell-specific behavior. The prior attempt at Vitest spawn tests stalled because it coupled e2e coverage with `pnpm pack` installs, which fail in network-restricted environments. With those findings incorporated, we now need an approved plan to realign the work.
+
+## What Changes
+- Adopt a phased strategy that first stabilizes direct spawn testing of the built CLI (`node dist/cli/index.js`) using lightweight fixtures and a shared `runCLI` helper.
+- Expand coverage once the spawn harness is stable, keeping the initial matrix focused on bash jobs for Linux/macOS and `pwsh` on Windows while exercising both the direct `node dist/cli/index.js` invocation and the bin shim with non-TTY defaults and captured diagnostics.
+- Treat packaging/install validation as an optional CI safeguard: when a runner has registry access, run a simple pnpm-based pack→install→smoke-test flow; otherwise document it as out of scope while closing remaining hardening items.
+- Close out the remaining cross-shell hardening items: ensure `.gitattributes` covers packaged assets, enforce executable bits for CLI shims during CI, and finish the pending SIGINT handling improvements.
+
+## Impact
+- Tests: add `test/cli-e2e` spawn suite, create the shared `runCLI` helper, and adjust `vitest.setup.ts` as needed.
+- Tooling: update GitHub Actions workflows with the lightweight matrix above and (optionally) a packaging install check where network is available.
+- Docs: note phase progress and any limitations inline in this proposal (or the relevant spec) so future phases have clear context.
+
+### Phase 1 Status
+- Shared `test/helpers/run-cli.ts` guarantees the CLI bundle exists before spawning and enforces non-TTY defaults for every invocation.
+- New `test/cli-e2e/basic.test.ts` covers `--help`, `--version`, a successful `validate --all --json`, and an unknown-item error path against the `tmp-init` fixture copy.
+- Legacy top-level `validate` exec tests now rely on `runCLI`, avoiding manual `execSync` usage while keeping their fixture authoring intact.
+- CI matrix groundwork is in place (bash on Linux/macOS, pwsh on Windows) so the spawn suite runs the same way the helper does across supported shells.
@@ -0,0 +1,9 @@
+## 1. Phase 1 – Stabilize Local Spawn Coverage
+- [x] 1.1 Add `test/helpers/run-cli.ts` that ensures the build runs once and executes `node dist/cli/index.js` with non-TTY defaults; update `vitest.setup.ts` to reuse the shared build step.
+- [x] 1.2 Seed `test/cli-e2e` using the minimal fixture set (`tmp-init` or copy) to cover help/version, a happy-path `validate`, and a representative error flow via the new helper.
+- [x] 1.3 Migrate the highest-value existing CLI exec tests (e.g., validate) onto `runCLI` and summarize Phase 1 coverage in this proposal for the next phase.
+
+## 2. Phase 2 – Expand Cross-Shell Validation
+- [x] 2.1 Exercise both entry points (`node dist/cli/index.js`, `bin/openspec.js`) in the spawn suite and add diagnostics for shell/OS context.
+- [x] 2.2 Extend GitHub Actions to run the spawn suite on bash jobs for Linux/macOS and a `pwsh` job on Windows; capture shell/OS diagnostics and note follow-ups for additional shells.
+
@@ -21,5 +21,5 @@

 ## 5. Optional (Not Needed Now)
 - [x] 5.1 Add optional root param to discovery helpers (default process.cwd())
- [ ] 5.2 Consider threading root through command constructors if ever required
+

@@ -0,0 +1,12 @@
+## 1. Planning & Spec Updates
+- [x] 1.1 Confirm overlap with `add-multi-agent-init` and coordinate extend-mode flow
+- [x] 1.2 Update `openspec/specs/cli-init/spec.md` to capture multi-select onboarding requirements
+
+## 2. Implementation
+- [x] 2.1 Add multi-select support to the `openspec init` prompt, including indicators for existing tool configs
+- [x] 2.2 Enhance success messaging to summarize created/refreshed assets per tool
+- [x] 2.3 Ensure shared instruction template is applied consistently (CLAUDE.md, AGENTS.md, slash commands)
+
+## 3. Quality
+- [x] 3.1 Expand unit tests for init/update flows covering multi-select and summaries
+- [x] 3.2 Perform `openspec init` smoke test in a temp directory (document output)
@@ -26,10 +26,6 @@
  - Archive documentation
  - Change proposals

-## 6. Add Deprecation Notice (Optional Phase)
- [ ] Consider adding a deprecation warning before full removal
- [ ] Provide helpful message directing users to `openspec show` command
-
 ## 7. Testing
 - [x] Ensure all tests pass after removal
 - [x] Verify CLI help text no longer shows diff command
@@ -25,12 +25,16 @@ The command SHALL generate required template files with appropriate content for

 ### Requirement: AI Tool Configuration Details

+The command SHALL properly configure selected AI tools with OpenSpec-specific instructions using a marker system.
+
 #### Scenario: Creating new CLAUDE.md
 - **WHEN** CLAUDE.md does not exist
 - **THEN** create new file with OpenSpec content wrapped in markers including reference to `@openspec/AGENTS.md`

 ### Requirement: Success Output

+The command SHALL provide clear, actionable next steps upon successful initialization.
+
 #### Scenario: Displaying success message
 - **WHEN** initialization completes successfully
 - **THEN** include prompt: "Please explain the OpenSpec workflow from openspec/AGENTS.md and how I should work with you on this project"
@@ -0,0 +1,19 @@
+# Update Markdown Parser CRLF Handling
+
+## Problem
+Windows users report that `openspec validate` raises “Change must have a Why section” even when the section exists (see GitHub issue #77). The CLI currently splits markdown on `\n` and compares headers without stripping `\r`, so files saved with CRLF line endings keep a trailing carriage return in the header token. As a result the parser fails to detect `## Why`/`## What Changes`, triggering false validation errors and breaking the workflow on Windows-default editors.
+
+## Solution
+- Normalize markdown content inside the parser so CRLF and lone-CR inputs are treated as `\n` before section detection, trimming any carriage returns from titles and content comparisons.
+- Reuse the normalized reader everywhere `MarkdownParser` is constructed to keep behavior consistent for validation, view, spec, and list flows.
+- Add regression coverage that reproduces the failure (unit test around `parseChange` and a CLI spawn/e2e test that writes a CRLF change then runs `openspec validate`).
+- Update the `cli-validate` spec to codify the expectation that required sections are recognized regardless of line-ending style.
+
+## Benefits
+- Restores correct validation behavior for Windows editors without requiring manual line-ending conversion.
+- Locks in the fix with targeted tests so future parser refactors keep cross-platform support.
+- Clarifies the spec so downstream work (e.g., cross-shell e2e plan) understands the non-negotiable behavior.
+
+## Risks
+- Low: parser normalization touches shared code paths that parse specs and changes; need to ensure no regressions in other command consumers (mitigated by existing parser tests plus the new CRLF fixtures).
+
@@ -0,0 +1,9 @@
+## ADDED Requirements
+### Requirement: Parser SHALL handle cross-platform line endings
+The markdown parser SHALL correctly identify sections regardless of line ending format (LF, CRLF, CR).
+
+#### Scenario: Required sections parsed with CRLF line endings
+- **GIVEN** a change proposal markdown saved with CRLF line endings
+- **AND** the document contains `## Why` and `## What Changes`
+- **WHEN** running `openspec validate <change-id>`
+- **THEN** validation SHALL recognize the sections and NOT raise parsing errors
@@ -0,0 +1,11 @@
+## 1. Guard the regression
+- [x] 1.1 Add a unit test that feeds a CRLF change document into `MarkdownParser.parseChange` and asserts `Why`/`What Changes` are detected.
+- [x] 1.2 Add a CLI spawn/e2e test that writes a CRLF change, runs `openspec validate`, and expects success.
+
+## 2. Normalize parsing
+- [x] 2.1 Normalize line endings when constructing `MarkdownParser` so headers and content comparisons ignore `\r`.
+- [x] 2.2 Ensure all CLI entry points (validate, view, spec conversion) reuse the normalized parser path.
+
+## 3. Document and verify
+- [x] 3.1 Update the `cli-validate` spec with a scenario covering CRLF line endings.
+- [x] 3.2 Run the parser and CLI test suites (`pnpm test`, relevant spawn tests) to confirm the fix.
@@ -0,0 +1,12 @@
+## Why
+Validation errors like "no deltas found" or "missing requirement text" do not tell agents how to recover, leading to repeated failures. Making error output specific about headers, required text, and next actions will help assistants fix issues in a single pass.
+
+## What Changes
+- Extend `openspec validate` error reporting so each failure names the exact header, file, and expected structure, including concrete examples of compliant Markdown.
+- Tailor messages for the most common mistakes (missing delta sections, absent descriptive requirement text, missing scenarios) with actionable fixes and suggested debug commands.
+- Update docs/help output so the improved messaging is discoverable (e.g., `--help`, troubleshooting section).
+- Add regression coverage to lock in the richer messaging for the top validation paths.
+
+## Impact
+- Affected specs: `specs/cli-validate`
+- Affected code: `src/commands/validate.ts`, `src/core/validation`, `docs/`
@@ -0,0 +1,39 @@
+## MODIFIED Requirements
+### Requirement: Validation SHALL provide actionable remediation steps
+Validation output SHALL include specific guidance to fix each error, including expected structure, example headers, and suggested commands to verify fixes.
+
+#### Scenario: No deltas found in change
+- **WHEN** validating a change with zero parsed deltas
+- **THEN** show error "No deltas found" with guidance:
+  - Explain that change specs must include `## ADDED Requirements`, `## MODIFIED Requirements`, `## REMOVED Requirements`, or `## RENAMED Requirements`
+  - Remind authors that files must live under `openspec/changes/{id}/specs/<capability>/spec.md`
+  - Include an explicit note: "Spec delta files cannot start with titles before the operation headers"
+  - Suggest running `openspec change show {id} --json --deltas-only` for debugging
+
+#### Scenario: Missing required sections
+- **WHEN** a required section is missing
+- **THEN** include expected header names and a minimal skeleton:
+  - For Spec: `## Purpose`, `## Requirements`
+  - For Change: `## Why`, `## What Changes`
+  - Provide an example snippet of the missing section with placeholder prose ready to copy
+  - Mention the quick-reference section in `openspec/AGENTS.md` as the authoritative template
+
+#### Scenario: Missing requirement descriptive text
+- **WHEN** a requirement header lacks descriptive text before scenarios
+- **THEN** emit an error explaining that `### Requirement:` lines must be followed by narrative text before any `#### Scenario:` headers
+  - Show compliant example: "### Requirement: Foo" followed by "The system SHALL ..."
+  - Suggest adding 1-2 sentences describing the normative behavior prior to listing scenarios
+  - Reference the pre-validation checklist in `openspec/AGENTS.md`
+
+### Requirement: Validator SHALL detect likely misformatted scenarios and warn with a fix
+The validator SHALL recognize bulleted lines that look like scenarios (e.g., lines beginning with WHEN/THEN/AND) and emit a targeted warning with a conversion example to `#### Scenario:`.
+
+#### Scenario: Bulleted WHEN/THEN under a Requirement
+- **WHEN** bullets that start with WHEN/THEN/AND are found under a requirement without any `#### Scenario:` headers
+- **THEN** emit warning: "Scenarios must use '#### Scenario:' headers", and show a conversion template:
+```
+#### Scenario: Short name
+- **WHEN** ...
+- **THEN** ...
+- **AND** ...
+```
@@ -0,0 +1,12 @@
+## 1. Messaging enhancements
+- [ ] 1.1 Inventory current validation failures and map each to the desired message improvements.
+- [ ] 1.2 Implement structured error builders that include file paths, normalized header names, and example fixes.
+- [ ] 1.3 Ensure `openspec validate --help` and troubleshooting docs mention the richer messages and debug tips.
+
+## 2. Tests
+- [ ] 2.1 Add unit tests for representative errors (no deltas, missing requirement body, missing scenarios) asserting the new wording.
+- [ ] 2.2 Add integration coverage verifying the Next steps footer reflects contextual guidance.
+
+## 3. Documentation
+- [ ] 3.1 Update troubleshooting sections and CLI docs with sample output from the enhanced errors.
+- [ ] 3.2 Note the change in CHANGELOG or release notes if applicable.
@@ -0,0 +1,12 @@
+## Why
+Agents fumble proposal formatting because the essential Markdown templates and formatting rules are buried mid-document. Reorganizing `openspec/AGENTS.md` with a prominent quick-reference and embedded examples will help assistants follow the process without guesswork.
+
+## What Changes
+- Restructure `openspec/AGENTS.md` so file formats and scaffold templates appear in a top-level quick-reference section before workflow prose.
+- Embed copy/paste templates for `proposal.md`, `tasks.md`, `design.md`, and spec deltas alongside inline examples within the workflow steps.
+- Add a pre-validation checklist that highlights the most common formatting pitfalls before running `openspec validate`.
+- Split content into beginner vs. advanced sections to progressively disclose complexity while keeping advanced guidance accessible.
+
+## Impact
+- Affected specs: `specs/docs-agent-instructions`
+- Affected code: `openspec/AGENTS.md`, `docs/`
@@ -0,0 +1,33 @@
+## ADDED Requirements
+### Requirement: Quick Reference Placement
+The AI instructions SHALL begin with a quick-reference section that surfaces required file structures, templates, and formatting rules before any narrative guidance.
+
+#### Scenario: Loading templates at the top
+- **WHEN** `openspec/AGENTS.md` is regenerated or updated
+- **THEN** the first substantive section after the title SHALL provide copy-ready headings for `proposal.md`, `tasks.md`, spec deltas, and scenario formatting
+- **AND** link each template to the corresponding workflow step for deeper reading
+
+### Requirement: Embedded Templates and Examples
+`openspec/AGENTS.md` SHALL include complete copy/paste templates and inline examples exactly where agents make corresponding edits.
+
+#### Scenario: Providing file templates
+- **WHEN** authors reach the workflow guidance for drafting proposals and deltas
+- **THEN** provide fenced Markdown templates that match the required structure (`## Why`, `## ADDED Requirements`, `#### Scenario:` etc.)
+- **AND** accompany each template with a brief example showing correct header usage and scenario bullets
+
+### Requirement: Pre-validation Checklist
+`openspec/AGENTS.md` SHALL offer a concise pre-validation checklist that highlights common formatting mistakes before running `openspec validate`.
+
+#### Scenario: Highlighting common validation failures
+- **WHEN** a reader reaches the validation guidance
+- **THEN** present a checklist reminding them to verify requirement headers, scenario formatting, and delta sections
+- **AND** include reminders about at least `#### Scenario:` usage and descriptive requirement text before scenarios
+
+### Requirement: Progressive Disclosure of Workflow Guidance
+The documentation SHALL separate beginner essentials from advanced topics so newcomers can focus on core steps without losing access to advanced workflows.
+
+#### Scenario: Organizing beginner and advanced sections
+- **WHEN** reorganizing `openspec/AGENTS.md`
+- **THEN** keep an introductory section limited to the minimum steps (scaffold, draft, validate, request review)
+- **AND** move advanced topics (multi-capability changes, archiving details, tooling deep dives) into clearly labeled later sections
+- **AND** provide anchor links from the quick-reference to those advanced sections
@@ -0,0 +1,11 @@
+## 1. Instruction redesign
+- [ ] 1.1 Draft a quick-reference section that surfaces file templates and formatting rules at the top of `openspec/AGENTS.md`.
+- [ ] 1.2 Reorganize the workflow narrative with inline examples and progressive disclosure for advanced topics.
+
+## 2. Templates and checklists
+- [ ] 2.1 Add copy/paste templates for proposal, tasks, design, and spec delta files.
+- [ ] 2.2 Insert a pre-validation checklist capturing common lint failures before running `openspec validate`.
+
+## 3. Documentation updates
+- [ ] 3.1 Update supporting docs or README pointers so contributors find the redesigned instructions.
+- [ ] 3.2 Confirm examples and references stay in sync with the new scaffold command guidance.
@@ -1,12 +0,0 @@
-## 1. Planning & Spec Updates
- [ ] 1.1 Confirm overlap with `add-multi-agent-init` and coordinate extend-mode flow
- [ ] 1.2 Update `openspec/specs/cli-init/spec.md` to capture multi-select onboarding requirements
-
-## 2. Implementation
- [ ] 2.1 Add multi-select support to the `openspec init` prompt, including indicators for existing tool configs
- [ ] 2.2 Enhance success messaging to summarize created/refreshed assets per tool
- [ ] 2.3 Ensure shared instruction template is applied consistently (CLAUDE.md, AGENTS.md, slash commands)
-
-## 3. Quality
- [ ] 3.1 Expand unit tests for init/update flows covering multi-select and summaries
- [ ] 3.2 Perform `openspec init` smoke test in a temp directory (document output)
@@ -0,0 +1,13 @@
+## Why
+The project root currently receives a full copy of the OpenSpec agent instructions, duplicating the content that also lives in `openspec/AGENTS.md`. When teams edit one copy but not the other, the files drift and onboarding assistants see conflicting guidance.
+
+## What Changes
+- Keep generating the complete template in `openspec/AGENTS.md` during `openspec init` and follow-up updates.
+- Replace the root-level file (`AGENTS.md` or `CLAUDE.md`, depending on tool selection) with a short hand-off that explains the project uses OpenSpec and points directly to `openspec/AGENTS.md`.
+- Add a dedicated stub template so both the init and update flows reuse the same minimal copy instructions.
+- Update CLI tests and documentation to reflect the new root-level messaging and ensure the OpenSpec marker block still protects future updates.
+
+## Impact
+- Affected specs: `cli-init`, `cli-update`
+- Affected code: `src/core/init.ts`, `src/core/update.ts`, `src/core/templates/agents-template.ts`
+- Update assets/readmes that mention the root `AGENTS.md` contents to reference the new stub message.
@@ -0,0 +1,15 @@
+## 1. Templates
+- [x] 1.1 Add a shared stub template that renders the root agent instructions hand-off message.
+- [x] 1.2 Ensure the stub covers both `AGENTS.md` and `CLAUDE.md` variants.
+
+## 2. Init Flow
+- [x] 2.1 Update `createInitArtifacts` to write the stub to the project root instead of the full instructions.
+- [x] 2.2 Preserve the managed block markers so future updates can overwrite the stub safely.
+
+## 3. Update Flow
+- [x] 3.1 Make the update command refresh the root stub rather than the full instructions.
+- [x] 3.2 Confirm the update log output still reflects the files that changed.
+
+## 4. Tests & Docs
+- [x] 4.1 Adjust CLI/init tests to match the new root content.
+- [x] 4.2 Document the stub message in `openspec/specs/cli-init` and `openspec/specs/cli-update` (and any relevant README snippets).
@@ -0,0 +1,15 @@
+## Why
+OpenSpec currently creates the root-level `AGENTS.md` stub only when teams explicitly select the "AGENTS.md standard" tool during `openspec init`. Projects that skip that checkbox never get a managed stub, so non-native assistants (Copilot, Codeium, etc.) have no entry point and later `openspec update` runs silently create the file without any context. We need to bake the stub into initialization, clarify the tool selection experience, and keep the update workflow aligned so every teammate lands on the right instructions from day one.
+
+## What Changes
+- Update `openspec init` so the root `AGENTS.md` stub is always generated (first run and extend mode) and refreshed from a shared utility instead of being tied to a tool selection.
+- Redesign the AI tool selection wizard to split options into "Natively supported" (Claude, Cursor, OpenCode, …) and an informational "Other tools" section that explains the always-on `AGENTS.md` hand-off.
+- Adjust CLI specs, prompts, and success messaging to reflect the new categories while keeping extend-mode behaviour consistent.
+- Update automated tests and fixtures to cover the unconditional stub creation and the reworked prompt flow.
+- Refresh documentation and onboarding snippets so they no longer describe the stub as opt-in and instead call out the new grouping.
+- Ensure `openspec update` continues to reconcile both `openspec/AGENTS.md` and the root stub, documenting the expected behaviour so mismatched setups self-heal.
+
+## Impact
+- Affected specs: `cli-init`, `cli-update`
+- Affected code: `src/core/init.ts`, `src/core/config.ts`, `src/core/configurators/agents.ts`, `src/core/templates/agents-root-stub.ts`, `src/core/update.ts`, related tests under `test/core/`
+- Docs & assets: README, CHANGELOG, any setup guides that reference choosing the "AGENTS.md standard" option
@@ -0,0 +1,32 @@
+## MODIFIED Requirements
+### Requirement: AI Tool Configuration
+The command SHALL configure AI coding assistants with OpenSpec instructions using a grouped selection experience so teams can enable native integrations while always provisioning guidance for other assistants.
+
+#### Scenario: Prompting for AI tool selection
+- **WHEN** run interactively
+- **THEN** present a multi-select wizard that separates options into two headings:
+  - **Natively supported providers** shows each available first-party integration (Claude Code, Cursor, OpenCode, …) with checkboxes
+  - **Other tools** explains that the root-level `AGENTS.md` stub is always generated for AGENTS-compatible assistants and cannot be deselected
+- **AND** mark already configured native tools with "(already configured)" to signal that choosing them will refresh managed content
+- **AND** keep disabled or unavailable providers labelled as "coming soon" so users know they cannot opt in yet
+- **AND** allow confirming the selection even when no native provider is chosen because the root stub remains enabled by default
+- **AND** change the base prompt copy in extend mode to "Which natively supported AI tools would you like to add or refresh?"
+
+### Requirement: Exit Code Adjustments
+`openspec init` SHALL treat extend mode without new native tool selections as a successful refresh.
+
+#### Scenario: Allowing empty extend runs
+- **WHEN** OpenSpec is already initialized and the user selects no additional natively supported tools
+- **THEN** complete successfully while refreshing the root `AGENTS.md` stub
+- **AND** exit with code 0
+
+## ADDED Requirements
+### Requirement: Root instruction stub
+`openspec init` SHALL always scaffold the root-level `AGENTS.md` hand-off so every teammate finds the primary OpenSpec instructions.
+
+#### Scenario: Creating root `AGENTS.md`
+- **GIVEN** the project may or may not already contain an `AGENTS.md` file
+- **WHEN** initialization completes in fresh or extend mode
+- **THEN** create or refresh `AGENTS.md` at the repository root using the managed marker block from `TemplateManager.getAgentsStandardTemplate()`
+- **AND** preserve any existing content outside the managed markers while replacing the stub text inside them
+- **AND** create the stub regardless of which native AI tools are selected
@@ -0,0 +1,10 @@
+## MODIFIED Requirements
+### Requirement: Tool-Agnostic Updates
+The update command SHALL refresh OpenSpec-managed files in a predictable manner while respecting each team's chosen tooling.
+
+#### Scenario: Updating files
+- **WHEN** updating files
+- **THEN** completely replace `openspec/AGENTS.md` with the latest template
+- **AND** create or refresh the root-level `AGENTS.md` stub using the managed marker block, even if the file was previously absent
+- **AND** update only the OpenSpec-managed sections inside existing AI tool files, leaving user-authored content untouched
+- **AND** avoid creating new native-tool configuration files (slash commands, CLAUDE.md, etc.) unless they already exist
@@ -0,0 +1,11 @@
+## 1. Implementation
+- [ ] 1.1 Refactor `openspec init` to always generate the root `AGENTS.md` stub (initial run and extend mode) via shared helper logic.
+- [ ] 1.2 Rework the AI tool selection wizard to surface "Natively supported" vs "Other tools" groupings and make the stub non-optional.
+- [ ] 1.3 Update CLI messaging, templates, and configurators so the new flow stays in sync across init and update commands.
+- [ ] 1.4 Refresh unit/integration tests to cover the unconditional stub and the regrouped prompt layout.
+- [ ] 1.5 Update documentation, README snippets, and CHANGELOG entries that mention the opt-in `AGENTS.md` experience.
+
+## 2. Validation
+- [ ] 2.1 Run `pnpm test` targeting CLI init/update suites.
+- [ ] 2.2 Execute `openspec validate update-cli-init-root-agents --strict`.
+- [ ] 2.3 Perform a manual smoke test: run `openspec init` in a temp directory, confirm stub + grouped prompts, rerun in extend mode.
@@ -0,0 +1,21 @@
+## Why
+Today's flow requires maintainers to merge the changeset PR, cut a tag, and draft the GitHub release by hand. Once the release is published on GitHub our existing automation pushes the package to npm, so the manual work centers on shepherding the release PR, updating version metadata, and keeping GitHub releases in sync with the changelog. Those repeated human steps slow the cycle time and increase the risk that the release/tag documentation falls out of sync with what was actually published to npm.
+
+## What Changes
+- Adopt the [changesets/action](https://github.com/changesets/action) workflow so pushes to `main` either open/update a release PR or, when the release PR merge lands, run our publish script automatically with the provided `NPM_TOKEN` and `GITHUB_TOKEN`.【5e2b47†L1-L43】【b9dad5†L13-L37】
+- Add a `release` npm script that builds the project and calls `changeset publish`, allowing the action to handle version bumps, changelog commits, and npm publishing in one command.【b9dad5†L13-L21】
+- Enable `createGithubReleases` in the action configuration so the workflow drafts GitHub releases from the published packages immediately after publishing.【5e2b47†L21-L38】
+- Document the automated release flow, required repository secrets, and how maintainers should handle failed publishes or hotfixes.
+
+## How the Maintainer Flow Changes
+| Step | Current process | Future process |
+| --- | --- | --- |
+| Prepare release | Merge changeset PR, wait for GitHub release automation, then manually draft release notes and tags | Merge changeset PR, the action updates/merges the release PR and handles version bumps automatically |
+| Publish npm package | Happens automatically after the GitHub release is published | Continues to happen automatically via `changeset publish`; no manual npm work |
+| GitHub release | Maintainers draft releases manually and ensure notes match the changelog | Action creates GitHub releases immediately after publishing, based on changeset information |
+| Clean up docs/process | Maintainers follow separate docs describing manual tagging and release steps | Update docs to remove manual tag/release steps and document the automated workflow |
+
+## Impact
+- Affected automation: `.github/workflows/release.yml`
+- Affected package metadata: `package.json` scripts
+- Documentation: `README.md` or `/docs` release instructions
@@ -0,0 +1,12 @@
+## 1. Release workflow automation
+- [ ] 1.1 Add a `.github/workflows/release.yml` that runs on pushes to `main`, sets up pnpm + Node 20, installs dependencies, and invokes `changesets/action@v1` with `publish: pnpm run release`.
+- [ ] 1.2 Configure the action with `createGithubReleases: true` and document required secrets (`NPM_TOKEN`, default `GITHUB_TOKEN`) plus recommended concurrency safeguards.
+- [ ] 1.3 Validate the workflow using `act` or a dry-run push to confirm the action opens release PRs when changesets exist and publishes when the release PR merge lands.
+
+## 2. Package release script
+- [ ] 2.1 Add a `release` script to `package.json` that builds the project and runs `changeset publish` using pnpm.
+- [ ] 2.2 Ensure the script respects the existing `prepare`/`prepublishOnly` hooks to avoid duplicate builds and update documentation or scripts if adjustments are needed.
+
+## 3. Documentation and recovery steps
+- [ ] 3.1 Update maintainer docs (e.g., README or `/docs`) with the end-to-end automated release flow, explicitly removing the manual tag/release steps that are no longer required and explaining how changesets drive the release PR.
+- [ ] 3.2 Document fallback steps for failed publishes (rerun workflow, manual publish) and the hotfix path when a release must be cut without pending changesets.
@@ -3,9 +3,7 @@
 ## Purpose

 The `openspec init` command SHALL create a complete OpenSpec directory structure in any project, enabling immediate adoption of OpenSpec conventions with support for multiple AI coding assistants.
-
 ## Requirements
-
 ### Requirement: Progress Indicators

 The command SHALL display progress indicators during initialization to provide clear feedback about each step.
@@ -21,11 +19,9 @@ The command SHALL display progress indicators during initialization to provide c
  - Then success: "✔ AI tools configured"

 ### Requirement: Directory Creation
-
 The command SHALL create the complete OpenSpec directory structure with all required directories and files.

 #### Scenario: Creating OpenSpec structure
-
 - **WHEN** `openspec init` is executed
 - **THEN** create the following directory structure:
 ```
@@ -38,13 +34,11 @@ openspec/
 ```

 ### Requirement: File Generation
-
 The command SHALL generate required template files with appropriate content for immediate use.

 #### Scenario: Generating template files
-
 - **WHEN** initializing OpenSpec
- **THEN** generate `AGENTS.md` containing complete OpenSpec instructions for AI assistants
+- **THEN** generate `openspec/AGENTS.md` containing complete OpenSpec instructions for AI assistants
 - **AND** generate `project.md` with project context template

 ### Requirement: AI Tool Configuration
@@ -54,10 +48,14 @@ The command SHALL configure AI coding assistants with OpenSpec instructions base
 #### Scenario: Prompting for AI tool selection

 - **WHEN** run interactively
- **THEN** prompt user to select AI tools to configure:
-  - Claude Code (updates/creates CLAUDE.md with OpenSpec markers)
-  - Cursor (future)
-  - Aider (future)
+- **THEN** prompt the user with "Which AI tools do you use?" using a multi-select menu
+- **AND** list every available tool with a checkbox:
+  - Claude Code (creates or refreshes CLAUDE.md and slash commands)
+  - Cursor (creates or refreshes `.cursor/commands/*` slash commands)
+  - AGENTS.md standard (creates or refreshes AGENTS.md stub with OpenSpec markers)
+- **AND** show "(already configured)" beside tools whose managed files exist so users understand selections will refresh content
+- **AND** treat disabled tools as "coming soon" and keep them unselectable
+- **AND** allow confirming with Enter after selecting one or more tools

 ### Requirement: AI Tool Configuration Details

@@ -67,112 +65,49 @@ The command SHALL properly configure selected AI tools with OpenSpec-specific in

 - **WHEN** Claude Code is selected
 - **THEN** create or update `CLAUDE.md` in the project root directory (not inside openspec/)
+- **AND** populate the managed block with a short stub that points teammates to `@/openspec/AGENTS.md`

 #### Scenario: Creating new CLAUDE.md

 - **WHEN** CLAUDE.md does not exist
- **THEN** create new file with OpenSpec content wrapped in markers:
+- **THEN** create new file with stub instructions wrapped in markers so the full workflow stays in `openspec/AGENTS.md`:
 ```markdown
 <!-- OPENSPEC:START -->
-# OpenSpec Project
+# OpenSpec Instructions

-This document provides instructions for AI coding assistants on how to use OpenSpec conventions for spec-driven development. Follow these rules precisely when working on OpenSpec-enabled projects.
+This project uses OpenSpec to manage AI assistant workflows.

-This project uses OpenSpec for spec-driven development. Specifications are the source of truth.
-
-See @openspec/AGENTS.md for detailed conventions and guidelines.
+- Full guidance lives in '@/openspec/AGENTS.md'.
+- Keep this managed block so 'openspec update' can refresh the instructions.
 <!-- OPENSPEC:END -->
 ```

-#### Scenario: Updating existing CLAUDE.md
-
- **WHEN** CLAUDE.md already exists
- **THEN** preserve all existing content
- **AND** insert OpenSpec content at the beginning of the file using markers
- **AND** ensure markers don't duplicate if they already exist
-
-#### Scenario: Managing content with markers
-
- **WHEN** using the marker system
- **THEN** use `<!-- OPENSPEC:START -->` to mark the beginning of managed content
- **AND** use `<!-- OPENSPEC:END -->` to mark the end of managed content
- **AND** allow OpenSpec to update its content without affecting user customizations
- **AND** preserve all content outside the markers intact
-
-WHY use markers:
- Users may have existing CLAUDE.md instructions they want to keep
- OpenSpec can update its instructions in future versions
- Clear boundary between OpenSpec-managed and user-managed content
-
 ### Requirement: Interactive Mode
-
 The command SHALL provide an interactive menu for AI tool selection with clear navigation instructions.

 #### Scenario: Displaying interactive menu
-
- **WHEN** run
- **THEN** prompt user with: "Which AI tool do you use?"
- **AND** show single-select menu with available tools:
-  - Claude Code
- **AND** show disabled options as "coming soon" (not selectable):
-  - Cursor (coming soon)
-  - Aider (coming soon)  
-  - Continue (coming soon)
-
-#### Scenario: Navigating the menu
-
- **WHEN** user is in the menu
- **THEN** allow arrow keys to move between options
- **AND** allow Enter key to select the highlighted option
+- **WHEN** run in fresh or extend mode
+- **THEN** present a looping select menu that lets users toggle tools with Enter and finish via a "Done" option
+- **AND** label already configured tools with "(already configured)" while keeping disabled options marked "coming soon"
+- **AND** change the prompt copy in extend mode to "Which AI tools would you like to add or refresh?"
+- **AND** display inline instructions clarifying that Enter toggles a tool and selecting "Done" confirms the list

 ### Requirement: Safety Checks
-
 The command SHALL perform safety checks to prevent overwriting existing structures and ensure proper permissions.

 #### Scenario: Detecting existing initialization
-
- **WHEN** `openspec/` directory already exists
- **THEN** display error with ora fail indicator:
-  - "✖ Error: OpenSpec seems to already be initialized. Use 'openspec update' to update the structure."
-
-#### Scenario: Checking write permissions
-
- **WHEN** checking initialization feasibility
- **THEN** verify write permissions in the target directory silently
- **AND** only display error if permissions are insufficient
+- **WHEN** the `openspec/` directory already exists
+- **THEN** inform the user that OpenSpec is already initialized, skip recreating the base structure, and enter an extend mode
+- **AND** continue to the AI tool selection step so additional tools can be configured
+- **AND** display the existing-initialization error message only when the user declines to add any AI tools

 ### Requirement: Success Output

 The command SHALL provide clear, actionable next steps upon successful initialization.

 #### Scenario: Displaying success message
-
 - **WHEN** initialization completes successfully
- **THEN** display actionable prompts for AI-driven workflow:
-```
-✔ OpenSpec initialized successfully!
-
-Next steps - Copy these prompts to Claude:
-
-────────────────────────────────────────────────────────────
-1. Populate your project context:
-   "Please read openspec/project.md and help me fill it out
-    with details about my project, tech stack, and conventions"
-
-2. Create your first change proposal:
-   "I want to add [YOUR FEATURE HERE]. Please create an
-    OpenSpec change proposal for this feature"
-
-3. Learn the OpenSpec workflow:
-   "Please explain the OpenSpec workflow from openspec/AGENTS.md
-    and how I should work with you on this project"
-────────────────────────────────────────────────────────────
-```
-
-The prompts SHALL:
- Be copy-pasteable for immediate use with AI tools
- Guide users through the AI-driven workflow
- Replace placeholder text ([YOUR FEATURE HERE]) with actual features
+- **THEN** include prompt: "Please explain the OpenSpec workflow from openspec/AGENTS.md and how I should work with you on this project"

 ### Requirement: Exit Codes

@@ -187,10 +122,56 @@ The command SHALL use consistent exit codes to indicate different failure modes.
  - 2: Insufficient permissions (reserved for future use)
  - 3: User cancelled operation (reserved for future use)

+### Requirement: Additional AI Tool Initialization
+`openspec init` SHALL allow users to add configuration files for new AI coding assistants after the initial setup.
+
+#### Scenario: Configuring an extra tool after initial setup
+- **GIVEN** an `openspec/` directory already exists and at least one AI tool file is present
+- **WHEN** the user runs `openspec init` and selects a different supported AI tool
+- **THEN** generate that tool's configuration files with OpenSpec markers the same way as during first-time initialization
+- **AND** leave existing tool configuration files unchanged except for managed sections that need refreshing
+- **AND** exit with code 0 and display a success summary highlighting the newly added tool files
+
+### Requirement: Success Output Enhancements
+`openspec init` SHALL summarize tool actions when initialization or extend mode completes.
+
+#### Scenario: Showing tool summary
+- **WHEN** the command completes successfully
+- **THEN** display a categorized summary of tools that were created, refreshed, or skipped (including already-configured skips)
+- **AND** personalize the "Next steps" header using the names of the selected tools, defaulting to a generic label when none remain
+
+### Requirement: Exit Code Adjustments
+`openspec init` SHALL treat extend mode with no selected tools as a guarded error.
+
+#### Scenario: Preventing empty extend runs
+- **WHEN** OpenSpec is already initialized and the user selects no additional tools
+- **THEN** exit with code 1 after showing the existing-initialization guidance message
+
+### Requirement: Slash Command Configuration
+The init command SHALL generate slash command files for supported editors using shared templates.
+
+#### Scenario: Generating slash commands for Claude Code
+- **WHEN** the user selects Claude Code during initialization
+- **THEN** create `.claude/commands/openspec/proposal.md`, `.claude/commands/openspec/apply.md`, and `.claude/commands/openspec/archive.md`
+- **AND** populate each file from shared templates so command text matches other tools
+- **AND** each template includes instructions for the relevant OpenSpec workflow stage
+
+#### Scenario: Generating slash commands for Cursor
+- **WHEN** the user selects Cursor during initialization
+- **THEN** create `.cursor/commands/openspec-proposal.md`, `.cursor/commands/openspec-apply.md`, and `.cursor/commands/openspec-archive.md`
+- **AND** populate each file from shared templates so command text matches other tools
+- **AND** each template includes instructions for the relevant OpenSpec workflow stage
+
+#### Scenario: Generating slash commands for OpenCode
+- **WHEN** the user selects OpenCode during initialization
+- **THEN** create `.opencode/commands/openspec-proposal.md`, `.opencode/commands/openspec-apply.md`, and `.opencode/commands/openspec-archive.md`
+- **AND** populate each file from shared templates so command text matches other tools
+- **AND** each template includes instructions for the relevant OpenSpec workflow stage
+
 ## Why

 Manual creation of OpenSpec structure is error-prone and creates adoption friction. A standardized init command ensures:
 - Consistent structure across all projects
 - Proper AI instruction files are always included
 - Quick onboarding for new projects
- Clear conventions from the start
+- Clear conventions from the start
@@ -5,22 +5,12 @@
 As a developer using OpenSpec, I want to update the OpenSpec instructions in my project when new versions are released, so that I can benefit from improvements to AI agent instructions.
 ## Requirements
 ### Requirement: Update Behavior
-
 The update command SHALL update OpenSpec instruction files to the latest templates in a team-friendly manner.

 #### Scenario: Running update command
-
 - **WHEN** a user runs `openspec update`
- **THEN** the command SHALL:
-  - Check if the `openspec` directory exists
-  - Replace `openspec/AGENTS.md` with the latest template (complete replacement)
-  - Update **only existing** AI tool configuration files (e.g., CLAUDE.md)
-    - Check each registered AI tool configurator
-    - For each configurator, check if its file exists
-    - Update only files that already exist using their markers
-    - Preserve user content outside markers
-    - **Never create new AI tool configuration files**
-  - Display success message listing updated files
+- **THEN** replace `openspec/AGENTS.md` with the latest template
+- **AND** if a root-level stub (`AGENTS.md`/`CLAUDE.md`) exists, refresh it so it points to `@/openspec/AGENTS.md`

 ### Requirement: Prerequisites

@@ -34,39 +24,56 @@ The command SHALL require an existing OpenSpec structure before allowing updates
 - **AND** exit with code 1

 ### Requirement: File Handling
-
 The update command SHALL handle file updates in a predictable and safe manner.

+#### Scenario: Updating files
+- **WHEN** updating files
+- **THEN** completely replace `openspec/AGENTS.md` with the latest template
+- **AND** if a root-level stub exists, update the managed block content so it keeps directing teammates to `@/openspec/AGENTS.md`
+
+### Requirement: Tool-Agnostic Updates
+The update command SHALL handle file updates in a predictable and safe manner while respecting team tool choices.
+
 #### Scenario: Updating files

 - **WHEN** updating files
 - **THEN** completely replace `openspec/AGENTS.md` with the latest template
+- **AND** update the root-level `AGENTS.md` using the OpenSpec markers only when that file already exists, keeping the stub content that links to `@/openspec/AGENTS.md`
 - **AND** update only the OpenSpec-managed blocks in **existing** AI tool files using markers
 - **AND** use the default directory name `openspec`
 - **AND** be idempotent (repeated runs have no additional effect)
- **AND** respect team members' AI tool choices by not creating unwanted files
-
-### Requirement: Tool-Agnostic Updates
-
-The update command SHALL update only existing AI tool configuration files and SHALL NOT create new ones.
-
-#### Scenario: Updating existing tool files
-
- **WHEN** a user runs `openspec update`
- **THEN** update each AI tool configuration file that exists (e.g., CLAUDE.md, COPILOT.md)
- **AND** do not create missing tool configuration files
- **AND** preserve user content outside OpenSpec markers
+- **AND** respect team members' AI tool choices by not creating additional tool files beyond the root `AGENTS.md`
+- **AND** do not create new root-level stub files when none are present

 ### Requirement: Core Files Always Updated
-
 The update command SHALL always update the core OpenSpec files and display an ASCII-safe success message.

 #### Scenario: Successful update
-
 - **WHEN** the update completes successfully
 - **THEN** replace `openspec/AGENTS.md` with the latest template
- **AND** update existing AI tool configuration files within markers
- **AND** display the message: "Updated OpenSpec instructions"
+- **AND** if a root-level stub exists, refresh it so it still directs contributors to `@/openspec/AGENTS.md`
+
+### Requirement: Slash Command Updates
+The update command SHALL refresh existing slash command files for configured tools without creating new ones.
+
+#### Scenario: Updating slash commands for Claude Code
+- **WHEN** `.claude/commands/openspec/` contains `proposal.md`, `apply.md`, and `archive.md`
+- **THEN** refresh each file using shared templates
+- **AND** ensure templates include instructions for the relevant workflow stage
+
+#### Scenario: Updating slash commands for Cursor
+- **WHEN** `.cursor/commands/` contains `openspec-proposal.md`, `openspec-apply.md`, and `openspec-archive.md`
+- **THEN** refresh each file using shared templates
+- **AND** ensure templates include instructions for the relevant workflow stage
+
+#### Scenario: Updating slash commands for OpenCode
+- **WHEN** `.opencode/command/` contains `openspec-proposal.md`, `openspec-apply.md`, and `openspec-archive.md`
+- **THEN** refresh each file using shared templates
+- **AND** ensure templates include instructions for the relevant workflow stage
+
+#### Scenario: Missing slash command file
+- **WHEN** a tool lacks a slash command file
+- **THEN** do not create a new file during update

 ## Edge Cases

@@ -101,4 +108,4 @@ Users SHALL be able to:
 The update process SHALL be:
 - Simple and fast (no version checking)
 - Predictable (same result every time)
- Self-contained (no network required)
+- Self-contained (no network required)
@@ -199,3 +199,12 @@ The validate command SHALL handle ambiguous names and explicit type overrides to
 - **THEN** the CLI SHALL not display interactive prompts
 - **AND** SHALL print non-interactive hints or chosen outputs as appropriate

+### Requirement: Parser SHALL handle cross-platform line endings
+The markdown parser SHALL correctly identify sections regardless of line ending format (LF, CRLF, CR).
+
+#### Scenario: Required sections parsed with CRLF line endings
+- **GIVEN** a change proposal markdown saved with CRLF line endings
+- **AND** the document contains `## Why` and `## What Changes`
+- **WHEN** running `openspec validate <change-id>`
+- **THEN** validation SHALL recognize the sections and NOT raise parsing errors
+
@@ -36,28 +36,14 @@ The dashboard SHALL display a summary section with key project metrics.
 - **THEN** summary shows zero counts for all metrics

 ### Requirement: Active Changes Display
-
 The dashboard SHALL show active changes with visual progress indicators.

-#### Scenario: Active changes with progress bars
-
- **WHEN** there are in-progress changes with tasks
- **THEN** system displays each change with change name left-aligned
- **AND** visual progress bar using Unicode characters
- **AND** percentage completion on the right
-
 #### Scenario: Active changes ordered by completion percentage
-
 - **WHEN** multiple active changes are displayed with progress information
 - **THEN** list them sorted by completion percentage ascending so 0% items appear first
 - **AND** treat missing progress values as 0% for ordering
 - **AND** break ties by change identifier in ascending alphabetical order to keep output deterministic

-#### Scenario: No active changes
-
- **WHEN** all changes are completed or no changes exist
- **THEN** active changes section is omitted from display
-
 ### Requirement: Completed Changes Display

 The dashboard SHALL list completed changes in a separate section.
@@ -14,11 +14,9 @@ OpenSpec conventions SHALL mandate a structured spec format with clear requireme
 - **THEN** authors SHALL use `### Requirement: ...` followed by at least one `#### Scenario: ...` section

 ### Requirement: Project Structure
-
 An OpenSpec project SHALL maintain a consistent directory structure for specifications and changes.

 #### Scenario: Initializing project structure
-
 - **WHEN** an OpenSpec project is initialized
 - **THEN** it SHALL have this structure:
 ```
@@ -1,6 +1,6 @@
 {
  "name": "@fission-ai/openspec",
-  "version": "0.3.0",
+  "version": "0.7.0",
  "description": "AI-native system for spec-driven development",
  "keywords": [
    "openspec",
@@ -17,7 +17,9 @@ export interface AIToolOption {
 }

 export const AI_TOOLS: AIToolOption[] = [
-  { name: 'Claude Code (✅ OpenSpec custom slash commands available)', value: 'claude', available: true, successLabel: 'Claude Code' },
-  { name: 'Cursor (✅ OpenSpec custom slash commands available)', value: 'cursor', available: true, successLabel: 'Cursor' },
-  { name: 'AGENTS.md (works with Codex, Amp, Copilot, …)', value: 'agents', available: true, successLabel: 'your AGENTS.md-compatible assistant' }
+  { name: 'Claude Code', value: 'claude', available: true, successLabel: 'Claude Code' },
+  { name: 'Cursor', value: 'cursor', available: true, successLabel: 'Cursor' },
+  { name: 'OpenCode', value: 'opencode', available: true, successLabel: 'OpenCode' },
+  { name: 'Kilo Code', value: 'kilocode', available: true, successLabel: 'Kilo Code' },
+  { name: 'AGENTS.md (works with Codex, Amp, VS Code, GitHub Copilot, …)', value: 'agents', available: false, successLabel: 'your AGENTS.md-compatible assistant' }
 ];
@@ -0,0 +1,21 @@
+import { SlashCommandConfigurator } from "./base.js";
+import { SlashCommandId } from "../../templates/index.js";
+
+const FILE_PATHS: Record<SlashCommandId, string> = {
+  proposal: ".kilocode/workflows/openspec-proposal.md",
+  apply: ".kilocode/workflows/openspec-apply.md",
+  archive: ".kilocode/workflows/openspec-archive.md"
+};
+
+export class KiloCodeSlashCommandConfigurator extends SlashCommandConfigurator {
+  readonly toolId = "kilocode";
+  readonly isAvailable = true;
+
+  protected getRelativePath(id: SlashCommandId): string {
+    return FILE_PATHS[id];
+  }
+
+  protected getFrontmatter(_id: SlashCommandId): string | undefined {
+    return undefined;
+  }
+}
@@ -0,0 +1,41 @@
+import { SlashCommandConfigurator } from "./base.js";
+import { SlashCommandId } from "../../templates/index.js";
+
+const FILE_PATHS: Record<SlashCommandId, string> = {
+  proposal: ".opencode/command/openspec-proposal.md",
+  apply: ".opencode/command/openspec-apply.md",
+  archive: ".opencode/command/openspec-archive.md",
+};
+
+const FRONTMATTER: Record<SlashCommandId, string> = {
+  proposal: `---
+agent: build
+description: Scaffold a new OpenSpec change and validate strictly.
+---
+The user has requested the following change proposal. Use the openspec instructions to create their change proposal.
+<UserRequest>
+  $ARGUMENTS
+</UserRequest>
+`,
+  apply: `---
+agent: build
+description: Implement an approved OpenSpec change and keep tasks in sync.
+---`,
+  archive: `---
+agent: build
+description: Archive a deployed OpenSpec change and update specs.
+---`,
+};
+
+export class OpenCodeSlashCommandConfigurator extends SlashCommandConfigurator {
+  readonly toolId = "opencode";
+  readonly isAvailable = true;
+
+  protected getRelativePath(id: SlashCommandId): string {
+    return FILE_PATHS[id];
+  }
+
+  protected getFrontmatter(id: SlashCommandId): string | undefined {
+    return FRONTMATTER[id];
+  }
+}
@@ -1,6 +1,8 @@
 import { SlashCommandConfigurator } from './base.js';
 import { ClaudeSlashCommandConfigurator } from './claude.js';
 import { CursorSlashCommandConfigurator } from './cursor.js';
+import { KiloCodeSlashCommandConfigurator } from './kilocode.js';
+import { OpenCodeSlashCommandConfigurator } from './opencode.js';

 export class SlashCommandRegistry {
  private static configurators: Map<string, SlashCommandConfigurator> = new Map();
@@ -8,9 +10,13 @@ export class SlashCommandRegistry {
  static {
    const claude = new ClaudeSlashCommandConfigurator();
    const cursor = new CursorSlashCommandConfigurator();
+    const kilocode = new KiloCodeSlashCommandConfigurator();
+    const opencode = new OpenCodeSlashCommandConfigurator();

    this.configurators.set(claude.toolId, claude);
    this.configurators.set(cursor.toolId, cursor);
+    this.configurators.set(kilocode.toolId, kilocode);
+    this.configurators.set(opencode.toolId, opencode);
  }

  static register(configurator: SlashCommandConfigurator): void {
@@ -43,7 +43,8 @@ export class JsonConverter {
  }

  private extractNameFromPath(filePath: string): string {
-    const parts = filePath.split('/');
+    const normalizedPath = filePath.replaceAll('\\', '/');
+    const parts = normalizedPath.split('/');
    
    for (let i = parts.length - 1; i >= 0; i--) {
      if (parts[i] === 'specs' || parts[i] === 'changes') {
@@ -53,7 +54,8 @@ export class JsonConverter {
      }
    }
    
-    const fileName = parts[parts.length - 1];
-    return fileName.replace('.md', '');
+    const fileName = parts[parts.length - 1] ?? '';
+    const dotIndex = fileName.lastIndexOf('.');
+    return dotIndex > 0 ? fileName.slice(0, dotIndex) : fileName;
  }
-}
+}
@@ -150,7 +150,7 @@ export class ChangeParser extends MarkdownParser {

  private parseRenames(content: string): Array<{ from: string; to: string }> {
    const renames: Array<{ from: string; to: string }> = [];
-    const lines = content.split('\n');
+    const lines = ChangeParser.normalizeContent(content).split('\n');
    
    let currentRename: { from?: string; to?: string } = {};
    
@@ -177,7 +177,8 @@ export class ChangeParser extends MarkdownParser {
  }

  private parseSectionsFromContent(content: string): Section[] {
-    const lines = content.split('\n');
+    const normalizedContent = ChangeParser.normalizeContent(content);
+    const lines = normalizedContent.split('\n');
    const sections: Section[] = [];
    const stack: Section[] = [];
    
@@ -12,10 +12,15 @@ export class MarkdownParser {
  private currentLine: number;

  constructor(content: string) {
-    this.lines = content.split('\n');
+    const normalized = MarkdownParser.normalizeContent(content);
+    this.lines = normalized.split('\n');
    this.currentLine = 0;
  }

+  protected static normalizeContent(content: string): string {
+    return content.replace(/\r\n?/g, '\n');
+  }
+
  parseSpec(name: string): Spec {
    const sections = this.parseSections();
    const purpose = this.findSection(sections, 'Purpose')?.content || '';
@@ -22,7 +22,8 @@ const REQUIREMENT_HEADER_REGEX = /^###\s*Requirement:\s*(.+)\s*$/;
 * Extracts the Requirements section from a spec file and parses requirement blocks.
 */
 export function extractRequirementsSection(content: string): RequirementsSectionParts {
-  const lines = content.split('\n');
+  const normalized = normalizeLineEndings(content);
+  const lines = normalized.split('\n');
  const reqHeaderIndex = lines.findIndex(l => /^##\s+Requirements\s*$/i.test(l));

  if (reqHeaderIndex === -1) {
@@ -102,11 +103,16 @@ export interface DeltaPlan {
  renamed: Array<{ from: string; to: string }>;
 }

+function normalizeLineEndings(content: string): string {
+  return content.replace(/\r\n?/g, '\n');
+}
+
 /**
 * Parse a delta-formatted spec change file content into a DeltaPlan with raw blocks.
 */
 export function parseDeltaSpec(content: string): DeltaPlan {
-  const sections = splitTopLevelSections(content);
+  const normalized = normalizeLineEndings(content);
+  const sections = splitTopLevelSections(normalized);
  const added = parseRequirementBlocksFromSection(sections['ADDED Requirements'] || '');
  const modified = parseRequirementBlocksFromSection(sections['MODIFIED Requirements'] || '');
  const removedNames = parseRemovedNames(sections['REMOVED Requirements'] || '');
@@ -136,7 +142,7 @@ function splitTopLevelSections(content: string): Record<string, string> {

 function parseRequirementBlocksFromSection(sectionBody: string): RequirementBlock[] {
  if (!sectionBody) return [];
-  const lines = sectionBody.split('\n');
+  const lines = normalizeLineEndings(sectionBody).split('\n');
  const blocks: RequirementBlock[] = [];
  let i = 0;
  while (i < lines.length) {
@@ -161,7 +167,7 @@ function parseRequirementBlocksFromSection(sectionBody: string): RequirementBloc
 function parseRemovedNames(sectionBody: string): string[] {
  if (!sectionBody) return [];
  const names: string[] = [];
-  const lines = sectionBody.split('\n');
+  const lines = normalizeLineEndings(sectionBody).split('\n');
  for (const line of lines) {
    const m = line.match(REQUIREMENT_HEADER_REGEX);
    if (m) {
@@ -180,7 +186,7 @@ function parseRemovedNames(sectionBody: string): string[] {
 function parseRenamedPairs(sectionBody: string): Array<{ from: string; to: string }> {
  if (!sectionBody) return [];
  const pairs: Array<{ from: string; to: string }> = [];
-  const lines = sectionBody.split('\n');
+  const lines = normalizeLineEndings(sectionBody).split('\n');
  let current: { from?: string; to?: string } = {};
  for (const line of lines) {
    const fromMatch = line.match(/^\s*-?\s*FROM:\s*`?###\s*Requirement:\s*(.+?)`?\s*$/);
@@ -0,0 +1,8 @@
+import chalk from 'chalk';
+
+export const PALETTE = {
+  white: chalk.hex('#f4f4f4'),
+  lightGray: chalk.hex('#c8c8c8'),
+  midGray: chalk.hex('#8a8a8a'),
+  darkGray: chalk.hex('#4a4a4a')
+};
@@ -0,0 +1,16 @@
+export const agentsRootStubTemplate = `# OpenSpec Instructions
+
+These instructions are for AI assistants working in this project.
+
+Always open \`@/openspec/AGENTS.md\` when the request:
+- Mentions planning or proposals (words like proposal, spec, change, plan)
+- Introduces new capabilities, breaking changes, architecture shifts, or big performance/security work
+- Sounds ambiguous and you need the authoritative spec before coding
+
+Use \`@/openspec/AGENTS.md\` to learn:
+- How to create and apply change proposals
+- Spec format and conventions
+- Project structure and guidelines
+
+Keep this managed block so 'openspec update' can refresh the instructions.
+`;
@@ -47,18 +47,20 @@ Skip proposal for:
 4. Run \`openspec validate <id> --strict\` and resolve any issues before sharing the proposal.

 ### Stage 2: Implementing Changes
+Track these steps as TODOs and complete them one by one.
 1. **Read proposal.md** - Understand what's being built
 2. **Read design.md** (if exists) - Review technical decisions
 3. **Read tasks.md** - Get implementation checklist
 4. **Implement tasks sequentially** - Complete in order
-5. **Mark complete immediately** - Update \`- [x]\` after each task
-6. **Approval gate** - Do not start implementation until the proposal is reviewed and approved
+5. **Confirm completion** - Ensure every item in \`tasks.md\` is finished before updating statuses
+6. **Update checklist** - After all work is done, set every task to \`- [x]\` so the list reflects reality
+7. **Approval gate** - Do not start implementation until the proposal is reviewed and approved

 ### Stage 3: Archiving Changes
 After deployment, create separate PR to:
 - Move \`changes/[name]/\` → \`changes/archive/YYYY-MM-DD-[name]/\`
 - Update \`specs/\` if capabilities changed
- Use \`openspec archive [change] --skip-specs\` for tooling-only changes
+- Use \`openspec archive [change] --skip-specs --yes\` for tooling-only changes
 - Run \`openspec validate --strict\` to confirm the archived change passes checks

 ## Before Any Task
@@ -95,7 +97,7 @@ openspec list --specs          # List specifications
 openspec show [item]           # Display change or spec
 openspec diff [change]         # Show spec differences
 openspec validate [item]       # Validate changes or specs
-openspec archive [change]      # Archive after deployment
+openspec archive [change] [--yes|-y]      # Archive after deployment (add --yes for non-interactive runs)

 # Project management
 openspec init [path]           # Initialize OpenSpec
@@ -117,6 +119,7 @@ openspec validate [change] --strict
 - \`--strict\` - Comprehensive validation
 - \`--no-interactive\` - Disable prompts
 - \`--skip-specs\` - Archive without spec updates
+- \`--yes\`/\`-y\` - Skip confirmation prompts (non-interactive archive)

 ## Directory Structure

@@ -447,7 +450,7 @@ openspec list              # What's in progress?
 openspec show [item]       # View details
 openspec diff [change]     # What's changing?
 openspec validate --strict # Is it correct?
-openspec archive [change]  # Mark complete
+openspec archive [change] [--yes|-y]  # Mark complete (add --yes for automation)
 \`\`\`

 Remember: Specs are truth. Changes are proposals. Keep them in sync.
@@ -1 +1 @@
-export { agentsTemplate as claudeTemplate } from './agents-template.js';
+export { agentsRootStubTemplate as claudeTemplate } from './agents-root-stub.js';
@@ -1,6 +1,7 @@
 import { agentsTemplate } from './agents-template.js';
 import { projectTemplate, ProjectContext } from './project-template.js';
 import { claudeTemplate } from './claude-template.js';
+import { agentsRootStubTemplate } from './agents-root-stub.js';
 import { getSlashCommandBody, SlashCommandId } from './slash-command-templates.js';

 export interface Template {
@@ -27,7 +28,7 @@ export class TemplateManager {
  }

  static getAgentsStandardTemplate(): string {
-    return agentsTemplate;
+    return agentsRootStubTemplate;
  }

  static getSlashCommandBody(id: SlashCommandId): string {
@@ -3,7 +3,7 @@ export type SlashCommandId = 'proposal' | 'apply' | 'archive';
 const baseGuardrails = `**Guardrails**
 - Favor straightforward, minimal implementations first and add complexity only when it is requested or clearly required.
 - Keep changes tightly scoped to the requested outcome.
- Refer to \`openspec/AGENTS.md\` if you need additional OpenSpec conventions or clarifications.`;
+- Refer to \`openspec/AGENTS.md\` (located inside the \`openspec/\` directory—run \`ls openspec\` or \`openspec update\` if you don't see it) if you need additional OpenSpec conventions or clarifications.`;

 const proposalGuardrails = `${baseGuardrails}\n- Identify any vague or ambiguous details and ask the necessary follow-up questions before editing files.`;

@@ -12,7 +12,7 @@ const proposalSteps = `**Steps**
 2. Choose a unique verb-led \`change-id\` and scaffold \`proposal.md\`, \`tasks.md\`, and \`design.md\` (when needed) under \`openspec/changes/<id>/\`.
 3. Map the change into concrete capabilities or requirements, breaking multi-scope efforts into distinct spec deltas with clear relationships and sequencing.
 4. Capture architectural reasoning in \`design.md\` when the solution spans multiple systems, introduces new patterns, or demands trade-off discussion before committing to specs.
-5. Draft spec deltas in \`changes/<id>/specs/\` using \`## ADDED|MODIFIED|REMOVED Requirements\` with at least one \`#### Scenario:\` per requirement and cross-reference related capabilities when relevant.
+5. Draft spec deltas in \`changes/<id>/specs/<capability>/spec.md\` (one folder per capability) using \`## ADDED|MODIFIED|REMOVED Requirements\` with at least one \`#### Scenario:\` per requirement and cross-reference related capabilities when relevant.
 6. Draft \`tasks.md\` as an ordered list of small, verifiable work items that deliver user-visible progress, include validation (tests, tooling), and highlight dependencies or parallelizable work.
 7. Validate with \`openspec validate <id> --strict\` and resolve every issue before sharing the proposal.`;

@@ -22,17 +22,19 @@ const proposalReferences = `**Reference**
 - Explore the codebase with \`rg <keyword>\`, \`ls\`, or direct file reads so proposals align with current implementation realities.`;

 const applySteps = `**Steps**
+Track these steps as TODOs and complete them one by one.
 1. Read \`changes/<id>/proposal.md\`, \`design.md\` (if present), and \`tasks.md\` to confirm scope and acceptance criteria.
 2. Work through tasks sequentially, keeping edits minimal and focused on the requested change.
-3. Mark each task \`- [x]\` immediately after completing it to keep the checklist in sync.
-4. Reference \`openspec list\` or \`openspec show <item>\` when additional context is required.`;
+3. Confirm completion before updating statuses—make sure every item in \`tasks.md\` is finished.
+4. Update the checklist after all work is done so each task is marked \`- [x]\` and reflects reality.
+5. Reference \`openspec list\` or \`openspec show <item>\` when additional context is required.`;

 const applyReferences = `**Reference**
 - Use \`openspec show <id> --json --deltas-only\` if you need additional context from the proposal while implementing.`;

 const archiveSteps = `**Steps**
 1. Identify the requested change ID (via the prompt or \`openspec list\`).
-2. Run \`openspec archive <id>\` to let the CLI move the change and apply spec updates (use \`--skip-specs\` only for tooling-only work).
+2. Run \`openspec archive <id> --yes\` to let the CLI move the change and apply spec updates without prompts (use \`--skip-specs\` only for tooling-only work).
 3. Review the command output to confirm the target specs were updated and the change landed in \`changes/archive/\`.
 4. Validate with \`openspec validate --strict\` and inspect with \`openspec show <id>\` if anything looks off.`;

@@ -1,10 +1,9 @@
 import path from 'path';
 import { FileSystemUtils } from '../utils/file-system.js';
-import { OPENSPEC_DIR_NAME, OPENSPEC_MARKERS } from './config.js';
-import { agentsTemplate } from './templates/agents-template.js';
-import { TemplateManager } from './templates/index.js';
+import { OPENSPEC_DIR_NAME } from './config.js';
 import { ToolRegistry } from './configurators/registry.js';
 import { SlashCommandRegistry } from './configurators/slash/registry.js';
+import { agentsTemplate } from './templates/agents-template.js';

 export class UpdateCommand {
  async execute(projectPath: string): Promise<void> {
@@ -19,41 +18,51 @@ export class UpdateCommand {

    // 2. Update AGENTS.md (full replacement)
    const agentsPath = path.join(openspecPath, 'AGENTS.md');
-    const rootAgentsPath = path.join(resolvedProjectPath, 'AGENTS.md');
-    const rootAgentsExisted = await FileSystemUtils.fileExists(rootAgentsPath);

    await FileSystemUtils.writeFile(agentsPath, agentsTemplate);
-    const agentsStandardContent = TemplateManager.getAgentsStandardTemplate();
-    await FileSystemUtils.updateFileWithMarkers(
-      rootAgentsPath,
-      agentsStandardContent,
-      OPENSPEC_MARKERS.start,
-      OPENSPEC_MARKERS.end
-    );

    // 3. Update existing AI tool configuration files only
    const configurators = ToolRegistry.getAll();
    const slashConfigurators = SlashCommandRegistry.getAll();
-    let updatedFiles: string[] = [];
-    let failedFiles: string[] = [];
-    let updatedSlashFiles: string[] = [];
-    let failedSlashTools: string[] = [];
-    
+    const updatedFiles: string[] = [];
+    const createdFiles: string[] = [];
+    const failedFiles: string[] = [];
+    const updatedSlashFiles: string[] = [];
+    const failedSlashTools: string[] = [];
+
    for (const configurator of configurators) {
-      const configFilePath = path.join(resolvedProjectPath, configurator.configFileName);
-      
-      // Only update if the file already exists
-      if (await FileSystemUtils.fileExists(configFilePath)) {
-        try {
-          if (!await FileSystemUtils.canWriteFile(configFilePath)) {
-            throw new Error(`Insufficient permissions to modify ${configurator.configFileName}`);
-          }
-          await configurator.configure(resolvedProjectPath, openspecPath);
-          updatedFiles.push(configurator.configFileName);
-        } catch (error) {
-          failedFiles.push(configurator.configFileName);
-          console.error(`Failed to update ${configurator.configFileName}: ${error instanceof Error ? error.message : String(error)}`);
+      const configFilePath = path.join(
+        resolvedProjectPath,
+        configurator.configFileName
+      );
+      const fileExists = await FileSystemUtils.fileExists(configFilePath);
+      const shouldConfigure =
+        fileExists || configurator.configFileName === 'AGENTS.md';
+
+      if (!shouldConfigure) {
+        continue;
+      }
+
+      try {
+        if (fileExists && !await FileSystemUtils.canWriteFile(configFilePath)) {
+          throw new Error(
+            `Insufficient permissions to modify ${configurator.configFileName}`
+          );
        }
+
+        await configurator.configure(resolvedProjectPath, openspecPath);
+        updatedFiles.push(configurator.configFileName);
+
+        if (!fileExists) {
+          createdFiles.push(configurator.configFileName);
+        }
+      } catch (error) {
+        failedFiles.push(configurator.configFileName);
+        console.error(
+          `Failed to update ${configurator.configFileName}: ${
+            error instanceof Error ? error.message : String(error)
+          }`
+        );
      }
    }

@@ -63,38 +72,56 @@ export class UpdateCommand {
      }

      try {
-        const updated = await slashConfigurator.updateExisting(resolvedProjectPath, openspecPath);
-        updatedSlashFiles = updatedSlashFiles.concat(updated);
+        const updated = await slashConfigurator.updateExisting(
+          resolvedProjectPath,
+          openspecPath
+        );
+        updatedSlashFiles.push(...updated);
      } catch (error) {
        failedSlashTools.push(slashConfigurator.toolId);
        console.error(
-          `Failed to update slash commands for ${slashConfigurator.toolId}: ${error instanceof Error ? error.message : String(error)}`
+          `Failed to update slash commands for ${slashConfigurator.toolId}: ${
+            error instanceof Error ? error.message : String(error)
+          }`
        );
      }
    }

-    // 4. Success message (ASCII-safe)
-    const instructionUpdates = ['openspec/AGENTS.md'];
-    instructionUpdates.push(`AGENTS.md${rootAgentsExisted ? '' : ' (created)'}`);
+    const summaryParts: string[] = [];
+    const instructionFiles: string[] = ['openspec/AGENTS.md'];

-    const messages: string[] = [`Updated OpenSpec instructions (${instructionUpdates.join(', ')})`];
-    
-    if (updatedFiles.length > 0) {
-      messages.push(`Updated AI tool files: ${updatedFiles.join(', ')}`);
+    if (updatedFiles.includes('AGENTS.md')) {
+      instructionFiles.push(
+        createdFiles.includes('AGENTS.md') ? 'AGENTS.md (created)' : 'AGENTS.md'
+      );
+    }
+
+    summaryParts.push(
+      `Updated OpenSpec instructions (${instructionFiles.join(', ')})`
+    );
+
+    const aiToolFiles = updatedFiles.filter((file) => file !== 'AGENTS.md');
+    if (aiToolFiles.length > 0) {
+      summaryParts.push(`Updated AI tool files: ${aiToolFiles.join(', ')}`);
    }

    if (updatedSlashFiles.length > 0) {
-      messages.push(`Updated slash commands: ${updatedSlashFiles.join(', ')}`);
-    }
-    
-    if (failedFiles.length > 0) {
-      messages.push(`Failed to update: ${failedFiles.join(', ')}`);
+      summaryParts.push(
+        `Updated slash commands: ${updatedSlashFiles.join(', ')}`
+      );
    }

-    if (failedSlashTools.length > 0) {
-      messages.push(`Failed slash command updates: ${failedSlashTools.join(', ')}`);
+    const failedItems = [
+      ...failedFiles,
+      ...failedSlashTools.map(
+        (toolId) => `slash command refresh (${toolId})`
+      ),
+    ];
+
+    if (failedItems.length > 0) {
+      summaryParts.push(`Failed to update: ${failedItems.join(', ')}`);
    }
-    
-    console.log(messages.join('\n'));
+
+    console.log(summaryParts.join(' | '));
  }
 }
@@ -38,11 +38,11 @@ export const VALIDATION_MESSAGES = {
  
  // Guidance snippets (appended to primary messages for remediation)
  GUIDE_NO_DELTAS:
-    'No deltas found. Ensure your change has a specs/ directory with .md files using delta headers (## ADDED/MODIFIED/REMOVED/RENAMED Requirements) and that each requirement includes at least one "#### Scenario:" block. Tip: run "openspec change show <change-id> --json --deltas-only" to inspect parsed deltas.',
+    'No deltas found. Ensure your change has a specs/ directory with capability folders (e.g. specs/http-server/spec.md) containing .md files that use delta headers (## ADDED/MODIFIED/REMOVED/RENAMED Requirements) and that each requirement includes at least one "#### Scenario:" block. Tip: run "openspec change show <change-id> --json --deltas-only" to inspect parsed deltas.',
  GUIDE_MISSING_SPEC_SECTIONS:
    'Missing required sections. Expected headers: "## Purpose" and "## Requirements". Example:\n## Purpose\n[brief purpose]\n\n## Requirements\n### Requirement: Clear requirement statement\nUsers SHALL ...\n\n#### Scenario: Descriptive name\n- **WHEN** ...\n- **THEN** ...',
  GUIDE_MISSING_CHANGE_SECTIONS:
    'Missing required sections. Expected headers: "## Why" and "## What Changes". Ensure deltas are documented in specs/ using delta headers.',
  GUIDE_SCENARIO_FORMAT:
    'Scenarios must use level-4 headers. Convert bullet lists into:\n#### Scenario: Short name\n- **WHEN** ...\n- **THEN** ...\n- **AND** ...',
-} as const;
+} as const;
@@ -331,7 +331,8 @@ export class Validator {
  }

  private extractNameFromPath(filePath: string): string {
-    const parts = filePath.split('/');
+    const normalizedPath = filePath.replaceAll('\\', '/');
+    const parts = normalizedPath.split('/');
    
    // Look for the directory name after 'specs' or 'changes'
    for (let i = parts.length - 1; i >= 0; i--) {
@@ -343,8 +344,9 @@ export class Validator {
    }
    
    // Fallback to filename without extension if not in expected structure
-    const fileName = parts[parts.length - 1];
-    return fileName.replace('.md', '');
+    const fileName = parts[parts.length - 1] ?? '';
+    const dotIndex = fileName.lastIndexOf('.');
+    return dotIndex > 0 ? fileName.slice(0, dotIndex) : fileName;
  }

  private createReport(issues: ValidationIssue[]): ValidationReport {
@@ -393,4 +395,4 @@ export class Validator {
    const matches = blockRaw.match(/^####\s+/gm);
    return matches ? matches.length : 0;
  }
-}
+}
@@ -1,6 +1,46 @@
 import { promises as fs } from 'fs';
 import path from 'path';

+function isMarkerOnOwnLine(content: string, markerIndex: number, markerLength: number): boolean {
+  let leftIndex = markerIndex - 1;
+  while (leftIndex >= 0 && content[leftIndex] !== '\n') {
+    const char = content[leftIndex];
+    if (char !== ' ' && char !== '\t' && char !== '\r') {
+      return false;
+    }
+    leftIndex--;
+  }
+
+  let rightIndex = markerIndex + markerLength;
+  while (rightIndex < content.length && content[rightIndex] !== '\n') {
+    const char = content[rightIndex];
+    if (char !== ' ' && char !== '\t' && char !== '\r') {
+      return false;
+    }
+    rightIndex++;
+  }
+
+  return true;
+}
+
+function findMarkerIndex(
+  content: string,
+  marker: string,
+  fromIndex = 0
+): number {
+  let currentIndex = content.indexOf(marker, fromIndex);
+
+  while (currentIndex !== -1) {
+    if (isMarkerOnOwnLine(content, currentIndex, marker.length)) {
+      return currentIndex;
+    }
+
+    currentIndex = content.indexOf(marker, currentIndex + marker.length);
+  }
+
+  return -1;
+}
+
 export class FileSystemUtils {
  static async createDirectory(dirPath: string): Promise<void> {
    await fs.mkdir(dirPath, { recursive: true });
@@ -70,10 +110,18 @@ export class FileSystemUtils {
    if (await this.fileExists(filePath)) {
      existingContent = await this.readFile(filePath);
      
-      const startIndex = existingContent.indexOf(startMarker);
-      const endIndex = existingContent.indexOf(endMarker);
-      
+      const startIndex = findMarkerIndex(existingContent, startMarker);
+      const endIndex = startIndex !== -1
+        ? findMarkerIndex(existingContent, endMarker, startIndex + startMarker.length)
+        : findMarkerIndex(existingContent, endMarker);
+
      if (startIndex !== -1 && endIndex !== -1) {
+        if (endIndex < startIndex) {
+          throw new Error(
+            `Invalid marker state in ${filePath}. End marker appears before start marker.`
+          );
+        }
+
        const before = existingContent.substring(0, startIndex);
        const after = existingContent.substring(endIndex + endMarker.length);
        existingContent = before + startMarker + '\n' + content + '\n' + endMarker + after;
@@ -109,4 +157,4 @@ export class FileSystemUtils {
      return false;
    }
  }
-}
+}
@@ -0,0 +1,56 @@
+import { afterAll, describe, it, expect } from 'vitest';
+import { promises as fs } from 'fs';
+import path from 'path';
+import { tmpdir } from 'os';
+import { runCLI, cliProjectRoot } from '../helpers/run-cli.js';
+
+const tempRoots: string[] = [];
+
+async function prepareFixture(fixtureName: string): Promise<string> {
+  const base = await fs.mkdtemp(path.join(tmpdir(), 'openspec-cli-e2e-'));
+  tempRoots.push(base);
+  const projectDir = path.join(base, 'project');
+  await fs.mkdir(projectDir, { recursive: true });
+  const fixtureDir = path.join(cliProjectRoot, 'test', 'fixtures', fixtureName);
+  await fs.cp(fixtureDir, projectDir, { recursive: true });
+  return projectDir;
+}
+
+afterAll(async () => {
+  await Promise.all(tempRoots.map((dir) => fs.rm(dir, { recursive: true, force: true })));
+});
+
+describe('openspec CLI e2e basics', () => {
+  it('shows help output', async () => {
+    const result = await runCLI(['--help']);
+    expect(result.exitCode).toBe(0);
+    expect(result.stdout).toContain('Usage: openspec');
+    expect(result.stderr).toBe('');
+  });
+
+  it('reports the package version', async () => {
+    const pkgRaw = await fs.readFile(path.join(cliProjectRoot, 'package.json'), 'utf-8');
+    const pkg = JSON.parse(pkgRaw);
+    const result = await runCLI(['--version']);
+    expect(result.exitCode).toBe(0);
+    expect(result.stdout.trim()).toBe(pkg.version);
+  });
+
+  it('validates the tmp-init fixture with --all --json', async () => {
+    const projectDir = await prepareFixture('tmp-init');
+    const result = await runCLI(['validate', '--all', '--json'], { cwd: projectDir });
+    expect(result.exitCode).toBe(0);
+    const output = result.stdout.trim();
+    expect(output).not.toBe('');
+    const json = JSON.parse(output);
+    expect(json.summary?.totals?.failed).toBe(0);
+    expect(json.items.some((item: any) => item.id === 'c1' && item.type === 'change')).toBe(true);
+  });
+
+  it('returns an error for unknown items in the fixture', async () => {
+    const projectDir = await prepareFixture('tmp-init');
+    const result = await runCLI(['validate', 'does-not-exist'], { cwd: projectDir });
+    expect(result.exitCode).toBe(1);
+    expect(result.stderr).toContain("Unknown item 'does-not-exist'");
+  });
+});
@@ -1,31 +1,33 @@
 import { describe, it, expect, beforeEach, afterEach } from 'vitest';
 import { promises as fs } from 'fs';
 import path from 'path';
-import { execSync } from 'child_process';
+import { runCLI } from '../helpers/run-cli.js';

 describe('top-level validate command', () => {
  const projectRoot = process.cwd();
  const testDir = path.join(projectRoot, 'test-validate-command-tmp');
  const changesDir = path.join(testDir, 'openspec', 'changes');
  const specsDir = path.join(testDir, 'openspec', 'specs');
-  const bin = path.join(projectRoot, 'bin', 'openspec.js');
-

  beforeEach(async () => {
    await fs.mkdir(changesDir, { recursive: true });
    await fs.mkdir(specsDir, { recursive: true });

    // Create a valid spec
-    const specContent = `## Purpose
-Valid spec for testing.
-
-## Requirements
-
-### Requirement: Foo
-Text
-
-#### Scenario: Bar
-Given A\nWhen B\nThen C`;
+    const specContent = [
+      '## Purpose',
+      'This spec ensures the validation harness exercises a deterministic alpha module for automated tests.',
+      '',
+      '## Requirements',
+      '',
+      '### Requirement: Alpha module SHALL produce deterministic output',
+      'The alpha module SHALL produce a deterministic response for validation.',
+      '',
+      '#### Scenario: Deterministic alpha run',
+      '- **GIVEN** a configured alpha module',
+      '- **WHEN** the module runs the default flow',
+      '- **THEN** the output matches the expected fixture result',
+    ].join('\n');
    await fs.mkdir(path.join(specsDir, 'alpha'), { recursive: true });
    await fs.writeFile(path.join(specsDir, 'alpha', 'spec.md'), specContent, 'utf-8');

@@ -33,10 +35,26 @@ Given A\nWhen B\nThen C`;
    const changeContent = `# Test Change\n\n## Why\nBecause reasons that are sufficiently long for validation.\n\n## What Changes\n- **alpha:** Add something`;
    await fs.mkdir(path.join(changesDir, 'c1'), { recursive: true });
    await fs.writeFile(path.join(changesDir, 'c1', 'proposal.md'), changeContent, 'utf-8');
+    const deltaContent = [
+      '## ADDED Requirements',
+      '### Requirement: Validator SHALL support alpha change deltas',
+      'The validator SHALL accept deltas provided by the test harness.',
+      '',
+      '#### Scenario: Apply alpha delta',
+      '- **GIVEN** the test change delta',
+      '- **WHEN** openspec validate runs',
+      '- **THEN** the validator reports the change as valid',
+    ].join('\n');
+    const c1DeltaDir = path.join(changesDir, 'c1', 'specs', 'alpha');
+    await fs.mkdir(c1DeltaDir, { recursive: true });
+    await fs.writeFile(path.join(c1DeltaDir, 'spec.md'), deltaContent, 'utf-8');

    // Duplicate name for ambiguity test
    await fs.mkdir(path.join(changesDir, 'dup'), { recursive: true });
    await fs.writeFile(path.join(changesDir, 'dup', 'proposal.md'), changeContent, 'utf-8');
+    const dupDeltaDir = path.join(changesDir, 'dup', 'specs', 'dup');
+    await fs.mkdir(dupDeltaDir, { recursive: true });
+    await fs.writeFile(path.join(dupDeltaDir, 'spec.md'), deltaContent, 'utf-8');
    await fs.mkdir(path.join(specsDir, 'dup'), { recursive: true });
    await fs.writeFile(path.join(specsDir, 'dup', 'spec.md'), specContent, 'utf-8');
  });
@@ -45,78 +63,71 @@ Given A\nWhen B\nThen C`;
    await fs.rm(testDir, { recursive: true, force: true });
  });

-  it('prints a helpful hint when no args in non-interactive mode', () => {
-    const originalCwd = process.cwd();
-    const originalEnv = { ...process.env };
-    try {
-      process.chdir(testDir);
-      process.env.OPEN_SPEC_INTERACTIVE = '0';
-      let err: any;
-      try {
-        execSync(`node ${bin} validate`, { encoding: 'utf-8' });
-      } catch (e) { err = e; }
-      expect(err).toBeDefined();
-      expect(err.status).not.toBe(0);
-      expect(err.stderr.toString()).toContain('Nothing to validate. Try one of:');
-    } finally {
-      process.chdir(originalCwd);
-      process.env = originalEnv;
-    }
+  it('prints a helpful hint when no args in non-interactive mode', async () => {
+    const result = await runCLI(['validate'], { cwd: testDir });
+    expect(result.exitCode).toBe(1);
+    expect(result.stderr).toContain('Nothing to validate. Try one of:');
  });

-  it('validates all with --all and outputs JSON summary', () => {
-    const originalCwd = process.cwd();
-    try {
-      process.chdir(testDir);
-      let outStr = '';
-      try {
-        outStr = execSync(`node ${bin} validate --all --json`, { encoding: 'utf-8' });
-      } catch (e: any) {
-        // If exit code is non-zero (e.g., on failures), still parse stdout JSON
-        outStr = e.stdout?.toString?.() ?? '';
-      }
-      const json = JSON.parse(outStr);
-      expect(Array.isArray(json.items)).toBe(true);
-      expect(json.summary?.totals?.items).toBeDefined();
-      expect(json.version).toBe('1.0');
-    } finally {
-      process.chdir(originalCwd);
-    }
+  it('validates all with --all and outputs JSON summary', async () => {
+    const result = await runCLI(['validate', '--all', '--json'], { cwd: testDir });
+    expect(result.exitCode).toBe(0);
+    const output = result.stdout.trim();
+    expect(output).not.toBe('');
+    const json = JSON.parse(output);
+    expect(Array.isArray(json.items)).toBe(true);
+    expect(json.summary?.totals?.items).toBeDefined();
+    expect(json.version).toBe('1.0');
  });

-  it('validates only specs with --specs and respects --concurrency', () => {
-    const originalCwd = process.cwd();
-    try {
-      process.chdir(testDir);
-      let outStr = '';
-      try {
-        outStr = execSync(`node ${bin} validate --specs --json --concurrency 1`, { encoding: 'utf-8' });
-      } catch (e: any) {
-        outStr = e.stdout?.toString?.() ?? '';
-      }
-      const json = JSON.parse(outStr);
-      // All items should be specs
-      expect(json.items.every((i: any) => i.type === 'spec')).toBe(true);
-    } finally {
-      process.chdir(originalCwd);
-    }
+  it('validates only specs with --specs and respects --concurrency', async () => {
+    const result = await runCLI(['validate', '--specs', '--json', '--concurrency', '1'], { cwd: testDir });
+    expect(result.exitCode).toBe(0);
+    const output = result.stdout.trim();
+    expect(output).not.toBe('');
+    const json = JSON.parse(output);
+    expect(json.items.every((i: any) => i.type === 'spec')).toBe(true);
  });

-  it('errors on ambiguous item names and suggests type override', () => {
-    const originalCwd = process.cwd();
-    try {
-      process.chdir(testDir);
-      let err: any;
-      try {
-        execSync(`node ${bin} validate dup`, { encoding: 'utf-8' });
-      } catch (e) { err = e; }
-      expect(err).toBeDefined();
-      expect(err.stderr.toString()).toContain('Ambiguous item');
-      expect(err.status).not.toBe(0);
-    } finally {
-      process.chdir(originalCwd);
-    }
+  it('errors on ambiguous item names and suggests type override', async () => {
+    const result = await runCLI(['validate', 'dup'], { cwd: testDir });
+    expect(result.exitCode).toBe(1);
+    expect(result.stderr).toContain('Ambiguous item');
+  });
+
+  it('accepts change proposals saved with CRLF line endings', async () => {
+    const changeId = 'crlf-change';
+    const toCrlf = (segments: string[]) => segments.join('\n').replace(/\n/g, '\r\n');
+
+    const crlfContent = toCrlf([
+      '# CRLF Proposal',
+      '',
+      '## Why',
+      'This change verifies validation works with Windows line endings.',
+      '',
+      '## What Changes',
+      '- **alpha:** Ensure validation passes on CRLF files',
+    ]);
+
+    await fs.mkdir(path.join(changesDir, changeId), { recursive: true });
+    await fs.writeFile(path.join(changesDir, changeId, 'proposal.md'), crlfContent, 'utf-8');
+
+    const deltaContent = toCrlf([
+      '## ADDED Requirements',
+      '### Requirement: Parser SHALL accept CRLF change proposals',
+      'The parser SHALL accept CRLF change proposals without manual edits.',
+      '',
+      '#### Scenario: Validate CRLF change',
+      '- **GIVEN** a change proposal saved with CRLF line endings',
+      '- **WHEN** a developer runs openspec validate on the proposal',
+      '- **THEN** validation succeeds without section errors',
+    ]);
+
+    const deltaDir = path.join(changesDir, changeId, 'specs', 'alpha');
+    await fs.mkdir(deltaDir, { recursive: true });
+    await fs.writeFile(path.join(deltaDir, 'spec.md'), deltaContent, 'utf-8');
+
+    const result = await runCLI(['validate', changeId], { cwd: testDir });
+    expect(result.exitCode).toBe(0);
  });
 });
-
-
@@ -43,7 +43,7 @@ describe('InitCommand', () => {
    selectionQueue = [];
    mockPrompt.mockReset();
    initCommand = new InitCommand({ prompt: mockPrompt });
-    
+
    // Mock console.log to suppress output during tests
    vi.spyOn(console, 'log').mockImplementation(() => {});
  });
@@ -56,14 +56,20 @@ describe('InitCommand', () => {
  describe('execute', () => {
    it('should create OpenSpec directory structure', async () => {
      queueSelections('claude', DONE);
-      
+
      await initCommand.execute(testDir);
-      
+
      const openspecPath = path.join(testDir, 'openspec');
      expect(await directoryExists(openspecPath)).toBe(true);
-      expect(await directoryExists(path.join(openspecPath, 'specs'))).toBe(true);
-      expect(await directoryExists(path.join(openspecPath, 'changes'))).toBe(true);
-      expect(await directoryExists(path.join(openspecPath, 'changes', 'archive'))).toBe(true);
+      expect(await directoryExists(path.join(openspecPath, 'specs'))).toBe(
+        true
+      );
+      expect(await directoryExists(path.join(openspecPath, 'changes'))).toBe(
+        true
+      );
+      expect(
+        await directoryExists(path.join(openspecPath, 'changes', 'archive'))
+      ).toBe(true);
    });

    it('should create AGENTS.md and project.md', async () => {
@@ -73,47 +79,58 @@ describe('InitCommand', () => {

      const openspecPath = path.join(testDir, 'openspec');
      expect(await fileExists(path.join(openspecPath, 'AGENTS.md'))).toBe(true);
-      expect(await fileExists(path.join(openspecPath, 'project.md'))).toBe(true);
+      expect(await fileExists(path.join(openspecPath, 'project.md'))).toBe(
+        true
+      );

-      const agentsContent = await fs.readFile(path.join(openspecPath, 'AGENTS.md'), 'utf-8');
+      const agentsContent = await fs.readFile(
+        path.join(openspecPath, 'AGENTS.md'),
+        'utf-8'
+      );
      expect(agentsContent).toContain('OpenSpec Instructions');
-      
-      const projectContent = await fs.readFile(path.join(openspecPath, 'project.md'), 'utf-8');
+
+      const projectContent = await fs.readFile(
+        path.join(openspecPath, 'project.md'),
+        'utf-8'
+      );
      expect(projectContent).toContain('Project Context');
    });

    it('should create CLAUDE.md when Claude Code is selected', async () => {
      queueSelections('claude', DONE);
-      
+
      await initCommand.execute(testDir);
-      
+
      const claudePath = path.join(testDir, 'CLAUDE.md');
      expect(await fileExists(claudePath)).toBe(true);
-      
+
      const content = await fs.readFile(claudePath, 'utf-8');
      expect(content).toContain('<!-- OPENSPEC:START -->');
-      expect(content).toContain('OpenSpec Instructions');
+      expect(content).toContain("@/openspec/AGENTS.md");
+      expect(content).toContain('openspec update');
      expect(content).toContain('<!-- OPENSPEC:END -->');
    });

    it('should update existing CLAUDE.md with markers', async () => {
      queueSelections('claude', DONE);
-      
+
      const claudePath = path.join(testDir, 'CLAUDE.md');
-      const existingContent = '# My Project Instructions\nCustom instructions here';
+      const existingContent =
+        '# My Project Instructions\nCustom instructions here';
      await fs.writeFile(claudePath, existingContent);
-      
+
      await initCommand.execute(testDir);
-      
+
      const updatedContent = await fs.readFile(claudePath, 'utf-8');
      expect(updatedContent).toContain('<!-- OPENSPEC:START -->');
-      expect(updatedContent).toContain('OpenSpec Instructions');
+      expect(updatedContent).toContain("@/openspec/AGENTS.md");
+      expect(updatedContent).toContain('openspec update');
      expect(updatedContent).toContain('<!-- OPENSPEC:END -->');
      expect(updatedContent).toContain('Custom instructions here');
    });

-    it('should create AGENTS.md in project root when AGENTS standard is selected', async () => {
-      queueSelections('agents', DONE);
+    it('should always create AGENTS.md in project root', async () => {
+      queueSelections(DONE);

      await initCommand.execute(testDir);

@@ -122,7 +139,8 @@ describe('InitCommand', () => {

      const content = await fs.readFile(rootAgentsPath, 'utf-8');
      expect(content).toContain('<!-- OPENSPEC:START -->');
-      expect(content).toContain('OpenSpec Instructions');
+      expect(content).toContain("@/openspec/AGENTS.md");
+      expect(content).toContain('openspec update');
      expect(content).toContain('<!-- OPENSPEC:END -->');

      const claudeExists = await fileExists(path.join(testDir, 'CLAUDE.md'));
@@ -134,9 +152,18 @@ describe('InitCommand', () => {

      await initCommand.execute(testDir);

-      const claudeProposal = path.join(testDir, '.claude/commands/openspec/proposal.md');
-      const claudeApply = path.join(testDir, '.claude/commands/openspec/apply.md');
-      const claudeArchive = path.join(testDir, '.claude/commands/openspec/archive.md');
+      const claudeProposal = path.join(
+        testDir,
+        '.claude/commands/openspec/proposal.md'
+      );
+      const claudeApply = path.join(
+        testDir,
+        '.claude/commands/openspec/apply.md'
+      );
+      const claudeArchive = path.join(
+        testDir,
+        '.claude/commands/openspec/archive.md'
+      );

      expect(await fileExists(claudeProposal)).toBe(true);
      expect(await fileExists(claudeApply)).toBe(true);
@@ -154,7 +181,9 @@ describe('InitCommand', () => {
      const archiveContent = await fs.readFile(claudeArchive, 'utf-8');
      expect(archiveContent).toContain('name: OpenSpec: Archive');
      expect(archiveContent).toContain('openspec archive <id>');
-      expect(archiveContent).toContain('`--skip-specs` only for tooling-only work');
+      expect(archiveContent).toContain(
+        '`--skip-specs` only for tooling-only work'
+      );
    });

    it('should create Cursor slash command files with templates', async () => {
@@ -162,9 +191,18 @@ describe('InitCommand', () => {

      await initCommand.execute(testDir);

-      const cursorProposal = path.join(testDir, '.cursor/commands/openspec-proposal.md');
-      const cursorApply = path.join(testDir, '.cursor/commands/openspec-apply.md');
-      const cursorArchive = path.join(testDir, '.cursor/commands/openspec-archive.md');
+      const cursorProposal = path.join(
+        testDir,
+        '.cursor/commands/openspec-proposal.md'
+      );
+      const cursorApply = path.join(
+        testDir,
+        '.cursor/commands/openspec-apply.md'
+      );
+      const cursorArchive = path.join(
+        testDir,
+        '.cursor/commands/openspec-archive.md'
+      );

      expect(await fileExists(cursorProposal)).toBe(true);
      expect(await fileExists(cursorApply)).toBe(true);
@@ -183,27 +221,110 @@ describe('InitCommand', () => {
      expect(archiveContent).toContain('openspec list --specs');
    });

+    it('should create OpenCode slash command files with templates', async () => {
+      queueSelections('opencode', DONE);
+
+      await initCommand.execute(testDir);
+
+      const openCodeProposal = path.join(
+        testDir,
+        '.opencode/command/openspec-proposal.md'
+      );
+      const openCodeApply = path.join(
+        testDir,
+        '.opencode/command/openspec-apply.md'
+      );
+      const openCodeArchive = path.join(
+        testDir,
+        '.opencode/command/openspec-archive.md'
+      );
+
+      expect(await fileExists(openCodeProposal)).toBe(true);
+      expect(await fileExists(openCodeApply)).toBe(true);
+      expect(await fileExists(openCodeArchive)).toBe(true);
+
+      const proposalContent = await fs.readFile(openCodeProposal, 'utf-8');
+      expect(proposalContent).toContain('agent: build');
+      expect(proposalContent).toContain(
+        'description: Scaffold a new OpenSpec change and validate strictly.'
+      );
+      expect(proposalContent).toContain('<!-- OPENSPEC:START -->');
+
+      const applyContent = await fs.readFile(openCodeApply, 'utf-8');
+      expect(applyContent).toContain('agent: build');
+      expect(applyContent).toContain(
+        'description: Implement an approved OpenSpec change and keep tasks in sync.'
+      );
+      expect(applyContent).toContain('Work through tasks sequentially');
+
+      const archiveContent = await fs.readFile(openCodeArchive, 'utf-8');
+      expect(archiveContent).toContain('agent: build');
+      expect(archiveContent).toContain(
+        'description: Archive a deployed OpenSpec change and update specs.'
+      );
+      expect(archiveContent).toContain('openspec list --specs');
+    });
+
+    it('should create Kilo Code workflows with templates', async () => {
+      queueSelections('kilocode', DONE);
+
+      await initCommand.execute(testDir);
+
+      const proposalPath = path.join(
+        testDir,
+        '.kilocode/workflows/openspec-proposal.md'
+      );
+      const applyPath = path.join(
+        testDir,
+        '.kilocode/workflows/openspec-apply.md'
+      );
+      const archivePath = path.join(
+        testDir,
+        '.kilocode/workflows/openspec-archive.md'
+      );
+
+      expect(await fileExists(proposalPath)).toBe(true);
+      expect(await fileExists(applyPath)).toBe(true);
+      expect(await fileExists(archivePath)).toBe(true);
+
+      const proposalContent = await fs.readFile(proposalPath, 'utf-8');
+      expect(proposalContent).toContain('<!-- OPENSPEC:START -->');
+      expect(proposalContent).toContain('**Guardrails**');
+      expect(proposalContent).not.toContain('---\n');
+
+      const applyContent = await fs.readFile(applyPath, 'utf-8');
+      expect(applyContent).toContain('Work through tasks sequentially');
+      expect(applyContent).not.toContain('---\n');
+
+      const archiveContent = await fs.readFile(archivePath, 'utf-8');
+      expect(archiveContent).toContain('openspec list --specs');
+      expect(archiveContent).not.toContain('---\n');
+    });
+
    it('should add new tool when OpenSpec already exists', async () => {
      queueSelections('claude', DONE, 'cursor', DONE);
      await initCommand.execute(testDir);
      await initCommand.execute(testDir);

-      const cursorProposal = path.join(testDir, '.cursor/commands/openspec-proposal.md');
+      const cursorProposal = path.join(
+        testDir,
+        '.cursor/commands/openspec-proposal.md'
+      );
      expect(await fileExists(cursorProposal)).toBe(true);
    });

-    it('should error when extend mode selects no tools', async () => {
+    it('should allow extend mode with no additional native tools', async () => {
      queueSelections('claude', DONE, DONE);
      await initCommand.execute(testDir);
-      await expect(initCommand.execute(testDir)).rejects.toThrow(/OpenSpec seems to already be initialized/);
+      await expect(initCommand.execute(testDir)).resolves.toBeUndefined();
    });

    it('should handle non-existent target directory', async () => {
      queueSelections('claude', DONE);
-      
+
      const newDir = path.join(testDir, 'new-project');
      await initCommand.execute(newDir);
-      
+
      const openspecPath = path.join(newDir, 'openspec');
      expect(await directoryExists(openspecPath)).toBe(true);
    });
@@ -211,21 +332,23 @@ describe('InitCommand', () => {
    it('should display success message with selected tool name', async () => {
      queueSelections('claude', DONE);
      const logSpy = vi.spyOn(console, 'log');
-      
+
      await initCommand.execute(testDir);
-      
+
      const calls = logSpy.mock.calls.flat().join('\n');
      expect(calls).toContain('Copy these prompts to Claude Code');
    });

    it('should reference AGENTS compatible assistants in success message', async () => {
-      queueSelections('agents', DONE);
+      queueSelections(DONE);
      const logSpy = vi.spyOn(console, 'log');

      await initCommand.execute(testDir);

      const calls = logSpy.mock.calls.flat().join('\n');
-      expect(calls).toContain('Copy these prompts to your AGENTS.md-compatible assistant');
+      expect(calls).toContain(
+        'Copy these prompts to your AGENTS.md-compatible assistant'
+      );
    });
  });

@@ -237,7 +360,9 @@ describe('InitCommand', () => {

      expect(mockPrompt).toHaveBeenCalledWith(
        expect.objectContaining({
-          baseMessage: expect.stringContaining('Which AI tools do you use?')
+          baseMessage: expect.stringContaining(
+            'Which natively supported AI tools do you use?'
+          ),
        })
      );
    });
@@ -247,7 +372,7 @@ describe('InitCommand', () => {
      queueSelections('claude', DONE);

      await initCommand.execute(testDir);
-      
+
      // When other tools are added, we'd test their specific configurations here
      const claudePath = path.join(testDir, 'CLAUDE.md');
      expect(await fileExists(claudePath)).toBe(true);
@@ -259,9 +384,21 @@ describe('InitCommand', () => {
      await initCommand.execute(testDir);

      const secondRunArgs = mockPrompt.mock.calls[1][0];
-      const claudeChoice = secondRunArgs.choices.find((choice: any) => choice.value === 'claude');
+      const claudeChoice = secondRunArgs.choices.find(
+        (choice: any) => choice.value === 'claude'
+      );
      expect(claudeChoice.configured).toBe(true);
    });
+
+    it('should preselect Kilo Code when workflows already exist', async () => {
+      queueSelections('kilocode', DONE, 'kilocode', DONE);
+      await initCommand.execute(testDir);
+      await initCommand.execute(testDir);
+
+      const secondRunArgs = mockPrompt.mock.calls[1][0];
+      const preselected = secondRunArgs.initialSelected ?? [];
+      expect(preselected).toContain('kilocode');
+    });
  });

  describe('error handling', () => {
@@ -269,16 +406,21 @@ describe('InitCommand', () => {
      // This is tricky to test cross-platform, but we can test the error message
      const readOnlyDir = path.join(testDir, 'readonly');
      await fs.mkdir(readOnlyDir);
-      
+
      // Mock the permission check to fail
      const originalCheck = fs.writeFile;
-      vi.spyOn(fs, 'writeFile').mockImplementation(async (filePath: any, ...args: any[]) => {
-        if (typeof filePath === 'string' && filePath.includes('.openspec-test-')) {
-          throw new Error('EACCES: permission denied');
+      vi.spyOn(fs, 'writeFile').mockImplementation(
+        async (filePath: any, ...args: any[]) => {
+          if (
+            typeof filePath === 'string' &&
+            filePath.includes('.openspec-test-')
+          ) {
+            throw new Error('EACCES: permission denied');
+          }
+          return originalCheck.call(fs, filePath, ...args);
        }
-        return originalCheck.call(fs, filePath, ...args);
-      });
-      
+      );
+
      queueSelections('claude', DONE);
      await expect(initCommand.execute(readOnlyDir)).rejects.toThrow(
        /Insufficient permissions/
@@ -169,6 +169,25 @@ Some general description of changes without specific deltas`;
      
      expect(change.deltas).toHaveLength(0);
    });
+
+    it('parses change documents saved with CRLF line endings', () => {
+      const crlfContent = [
+        '# CRLF Change',
+        '',
+        '## Why',
+        'Reasons on Windows editors should parse like POSIX environments.',
+        '',
+        '## What Changes',
+        '- **alpha:** Add cross-platform parsing coverage',
+      ].join('\r\n');
+
+      const parser = new MarkdownParser(crlfContent);
+      const change = parser.parseChange('crlf-change');
+
+      expect(change.why).toContain('Windows editors should parse');
+      expect(change.deltas).toHaveLength(1);
+      expect(change.deltas[0].spec).toBe('alpha');
+    });
  });

  describe('section parsing', () => {
@@ -15,11 +15,11 @@ describe('UpdateCommand', () => {
    // Create a temporary test directory
    testDir = path.join(os.tmpdir(), `openspec-test-${randomUUID()}`);
    await fs.mkdir(testDir, { recursive: true });
-    
+
    // Create openspec directory
    const openspecDir = path.join(testDir, 'openspec');
    await fs.mkdir(openspecDir, { recursive: true });
-    
+
    updateCommand = new UpdateCommand();
  });

@@ -43,7 +43,7 @@ More content after.`;
    await fs.writeFile(claudePath, initialContent);

    const consoleSpy = vi.spyOn(console, 'log');
-    
+
    // Execute update command
    await updateCommand.execute(testDir);

@@ -51,20 +51,26 @@ More content after.`;
    const updatedContent = await fs.readFile(claudePath, 'utf-8');
    expect(updatedContent).toContain('<!-- OPENSPEC:START -->');
    expect(updatedContent).toContain('<!-- OPENSPEC:END -->');
-    expect(updatedContent).toContain('OpenSpec Instructions');
+    expect(updatedContent).toContain("@/openspec/AGENTS.md");
+    expect(updatedContent).toContain('openspec update');
    expect(updatedContent).toContain('Some existing content here');
    expect(updatedContent).toContain('More content after');
-    
+
    // Check console output
    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
    expect(logMessage).toContain('AGENTS.md (created)');
    expect(logMessage).toContain('Updated AI tool files: CLAUDE.md');
    consoleSpy.mockRestore();
  });

  it('should refresh existing Claude slash command files', async () => {
-    const proposalPath = path.join(testDir, '.claude/commands/openspec/proposal.md');
+    const proposalPath = path.join(
+      testDir,
+      '.claude/commands/openspec/proposal.md'
+    );
    await fs.mkdir(path.dirname(proposalPath), { recursive: true });
    const initialContent = `---
 name: OpenSpec: Proposal
@@ -84,13 +90,19 @@ Old slash content
    const updated = await fs.readFile(proposalPath, 'utf-8');
    expect(updated).toContain('name: OpenSpec: Proposal');
    expect(updated).toContain('**Guardrails**');
-    expect(updated).toContain('Validate with `openspec validate <id> --strict`');
+    expect(updated).toContain(
+      'Validate with `openspec validate <id> --strict`'
+    );
    expect(updated).not.toContain('Old slash content');

    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
    expect(logMessage).toContain('AGENTS.md (created)');
-    expect(logMessage).toContain('Updated slash commands: .claude/commands/openspec/proposal.md');
+    expect(logMessage).toContain(
+      'Updated slash commands: .claude/commands/openspec/proposal.md'
+    );

    consoleSpy.mockRestore();
  });
@@ -98,7 +110,7 @@ Old slash content
  it('should not create CLAUDE.md if it does not exist', async () => {
    // Ensure CLAUDE.md does not exist
    const claudePath = path.join(testDir, 'CLAUDE.md');
-    
+
    // Execute update command
    await updateCommand.execute(testDir);

@@ -131,9 +143,79 @@ Old body
    expect(updated).not.toContain('Old body');

    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
    expect(logMessage).toContain('AGENTS.md (created)');
-    expect(logMessage).toContain('Updated slash commands: .cursor/commands/openspec-apply.md');
+    expect(logMessage).toContain(
+      'Updated slash commands: .cursor/commands/openspec-apply.md'
+    );
+
+    consoleSpy.mockRestore();
+  });
+
+  it('should refresh existing OpenCode slash command files', async () => {
+    const openCodePath = path.join(
+      testDir,
+      '.opencode/command/openspec-apply.md'
+    );
+    await fs.mkdir(path.dirname(openCodePath), { recursive: true });
+    const initialContent = `---
+name: /openspec-apply
+id: openspec-apply
+category: OpenSpec
+description: Old description
+---
+<!-- OPENSPEC:START -->
+Old body
+<!-- OPENSPEC:END -->`;
+    await fs.writeFile(openCodePath, initialContent);
+
+    const consoleSpy = vi.spyOn(console, 'log');
+
+    await updateCommand.execute(testDir);
+
+    const updated = await fs.readFile(openCodePath, 'utf-8');
+    expect(updated).toContain('id: openspec-apply');
+    expect(updated).toContain('Work through tasks sequentially');
+    expect(updated).not.toContain('Old body');
+
+    const [logMessage] = consoleSpy.mock.calls[0];
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
+    expect(logMessage).toContain('AGENTS.md (created)');
+    expect(logMessage).toContain(
+      'Updated slash commands: .opencode/command/openspec-apply.md'
+    );
+
+    consoleSpy.mockRestore();
+  });
+
+  it('should refresh existing Kilo Code workflows', async () => {
+    const kilocodePath = path.join(
+      testDir,
+      '.kilocode/workflows/openspec-apply.md'
+    );
+    await fs.mkdir(path.dirname(kilocodePath), { recursive: true });
+    const initialContent = `<!-- OPENSPEC:START -->
+Old body
+<!-- OPENSPEC:END -->`;
+    await fs.writeFile(kilocodePath, initialContent);
+
+    const consoleSpy = vi.spyOn(console, 'log');
+
+    await updateCommand.execute(testDir);
+
+    const updated = await fs.readFile(kilocodePath, 'utf-8');
+    expect(updated).toContain('Work through tasks sequentially');
+    expect(updated).not.toContain('Old body');
+    expect(updated.startsWith('<!-- OPENSPEC:START -->')).toBe(true);
+
+    const [logMessage] = consoleSpy.mock.calls[0];
+    expect(logMessage).toContain(
+      'Updated slash commands: .kilocode/workflows/openspec-apply.md'
+    );

    consoleSpy.mockRestore();
  });
@@ -145,7 +227,9 @@ Old body

    // Should only update OpenSpec instructions
    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
    expect(logMessage).toContain('AGENTS.md (created)');
    consoleSpy.mockRestore();
  });
@@ -157,23 +241,33 @@ Old body
    // For now, we test with just CLAUDE.md.
    const claudePath = path.join(testDir, 'CLAUDE.md');
    await fs.mkdir(path.dirname(claudePath), { recursive: true });
-    await fs.writeFile(claudePath, '<!-- OPENSPEC:START -->\nOld\n<!-- OPENSPEC:END -->');
+    await fs.writeFile(
+      claudePath,
+      '<!-- OPENSPEC:START -->\nOld\n<!-- OPENSPEC:END -->'
+    );

    const consoleSpy = vi.spyOn(console, 'log');
    await updateCommand.execute(testDir);

    // Should report updating with new format
    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
    expect(logMessage).toContain('AGENTS.md (created)');
    expect(logMessage).toContain('Updated AI tool files: CLAUDE.md');
    consoleSpy.mockRestore();
  });

  it('should skip creating missing slash commands during update', async () => {
-    const proposalPath = path.join(testDir, '.claude/commands/openspec/proposal.md');
+    const proposalPath = path.join(
+      testDir,
+      '.claude/commands/openspec/proposal.md'
+    );
    await fs.mkdir(path.dirname(proposalPath), { recursive: true });
-    await fs.writeFile(proposalPath, `---
+    await fs.writeFile(
+      proposalPath,
+      `---
 name: OpenSpec: Proposal
 description: Existing file
 category: OpenSpec
@@ -181,12 +275,17 @@ tags: [openspec, change]
 ---
 <!-- OPENSPEC:START -->
 Old content
-<!-- OPENSPEC:END -->`);
+<!-- OPENSPEC:END -->`
+    );

    await updateCommand.execute(testDir);

-    const applyExists = await FileSystemUtils.fileExists(path.join(testDir, '.claude/commands/openspec/apply.md'));
-    const archiveExists = await FileSystemUtils.fileExists(path.join(testDir, '.claude/commands/openspec/archive.md'));
+    const applyExists = await FileSystemUtils.fileExists(
+      path.join(testDir, '.claude/commands/openspec/apply.md')
+    );
+    const archiveExists = await FileSystemUtils.fileExists(
+      path.join(testDir, '.claude/commands/openspec/archive.md')
+    );

    expect(applyExists).toBe(false);
    expect(archiveExists).toBe(false);
@@ -195,7 +294,7 @@ Old content
  it('should never create new AI tool files', async () => {
    // Get all configurators
    const configurators = ToolRegistry.getAll();
-    
+
    // Execute update command
    await updateCommand.execute(testDir);

@@ -233,7 +332,8 @@ Old content

    const content = await fs.readFile(rootAgentsPath, 'utf-8');
    expect(content).toContain('<!-- OPENSPEC:START -->');
-    expect(content).toContain('OpenSpec Instructions');
+    expect(content).toContain("@/openspec/AGENTS.md");
+    expect(content).toContain('openspec update');
    expect(content).toContain('<!-- OPENSPEC:END -->');
  });

@@ -249,11 +349,14 @@ Old content
    const updated = await fs.readFile(rootAgentsPath, 'utf-8');
    expect(updated).toContain('# Custom intro');
    expect(updated).toContain('# Footnotes');
-    expect(updated).toContain('OpenSpec Instructions');
+    expect(updated).toContain("@/openspec/AGENTS.md");
+    expect(updated).toContain('openspec update');
    expect(updated).not.toContain('Old content');

    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md, AGENTS.md)');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md, AGENTS.md)'
+    );
    expect(logMessage).not.toContain('AGENTS.md (created)');

    consoleSpy.mockRestore();
@@ -261,7 +364,10 @@ Old content

  it('should throw error if openspec directory does not exist', async () => {
    // Remove openspec directory
-    await fs.rm(path.join(testDir, 'openspec'), { recursive: true, force: true });
+    await fs.rm(path.join(testDir, 'openspec'), {
+      recursive: true,
+      force: true,
+    });

    // Execute update command and expect error
    await expect(updateCommand.execute(testDir)).rejects.toThrow(
@@ -272,19 +378,24 @@ Old content
  it('should handle configurator errors gracefully', async () => {
    // Create CLAUDE.md file but make it read-only to cause an error
    const claudePath = path.join(testDir, 'CLAUDE.md');
-    await fs.writeFile(claudePath, '<!-- OPENSPEC:START -->\nOld\n<!-- OPENSPEC:END -->');
+    await fs.writeFile(
+      claudePath,
+      '<!-- OPENSPEC:START -->\nOld\n<!-- OPENSPEC:END -->'
+    );
    await fs.chmod(claudePath, 0o444); // Read-only

    const consoleSpy = vi.spyOn(console, 'log');
    const errorSpy = vi.spyOn(console, 'error');
    const originalWriteFile = FileSystemUtils.writeFile.bind(FileSystemUtils);
-    const writeSpy = vi.spyOn(FileSystemUtils, 'writeFile').mockImplementation(async (filePath, content) => {
-      if (filePath.endsWith('CLAUDE.md')) {
-        throw new Error('EACCES: permission denied, open');
-      }
+    const writeSpy = vi
+      .spyOn(FileSystemUtils, 'writeFile')
+      .mockImplementation(async (filePath, content) => {
+        if (filePath.endsWith('CLAUDE.md')) {
+          throw new Error('EACCES: permission denied, open');
+        }

-      return originalWriteFile(filePath, content);
-    });
+        return originalWriteFile(filePath, content);
+      });

    // Execute update command - should not throw
    await updateCommand.execute(testDir);
@@ -292,7 +403,9 @@ Old content
    // Should report the failure
    expect(errorSpy).toHaveBeenCalled();
    const [logMessage] = consoleSpy.mock.calls[0];
-    expect(logMessage).toContain('Updated OpenSpec instructions (openspec/AGENTS.md');
+    expect(logMessage).toContain(
+      'Updated OpenSpec instructions (openspec/AGENTS.md'
+    );
    expect(logMessage).toContain('AGENTS.md (created)');
    expect(logMessage).toContain('Failed to update: CLAUDE.md');

@@ -0,0 +1,7 @@
+# Test Change
+
+## Why
+Because reasons that are sufficiently long for validation.
+
+## What Changes
+- **alpha:** Add something
@@ -0,0 +1,8 @@
+## ADDED Requirements
+### Requirement: Parser SHALL accept CRLF change proposals
+The parser SHALL accept CRLF change proposals without manual edits.
+
+#### Scenario: Validate CRLF change
+- **GIVEN** a change proposal saved with CRLF line endings
+- **WHEN** a developer runs openspec validate on the proposal
+- **THEN** validation succeeds without section errors
@@ -0,0 +1,12 @@
+## Purpose
+This spec ensures the validation harness exercises a deterministic alpha module for automated tests.
+
+## Requirements
+
+### Requirement: Alpha module SHALL produce deterministic output
+The alpha module SHALL produce a deterministic response for validation.
+
+#### Scenario: Deterministic alpha run
+- **GIVEN** a configured alpha module
+- **WHEN** the module runs the default flow
+- **THEN** the output matches the expected fixture result
@@ -0,0 +1,139 @@
+import { spawn } from 'child_process';
+import { existsSync } from 'fs';
+import path from 'path';
+import { fileURLToPath } from 'url';
+
+const __filename = fileURLToPath(import.meta.url);
+const __dirname = path.dirname(__filename);
+
+const projectRoot = path.resolve(__dirname, '..', '..');
+const cliEntry = path.join(projectRoot, 'dist', 'cli', 'index.js');
+
+let buildPromise: Promise<void> | undefined;
+
+interface RunCommandOptions {
+  cwd?: string;
+  env?: NodeJS.ProcessEnv;
+}
+
+interface RunCLIOptions {
+  cwd?: string;
+  env?: NodeJS.ProcessEnv;
+  input?: string;
+  timeoutMs?: number;
+}
+
+export interface RunCLIResult {
+  exitCode: number | null;
+  signal: NodeJS.Signals | null;
+  stdout: string;
+  stderr: string;
+  timedOut: boolean;
+  command: string;
+}
+
+function runCommand(command: string, args: string[], options: RunCommandOptions = {}) {
+  return new Promise<void>((resolve, reject) => {
+    const child = spawn(command, args, {
+      cwd: options.cwd ?? projectRoot,
+      env: { ...process.env, ...options.env },
+      stdio: 'inherit',
+      shell: process.platform === 'win32',
+    });
+
+    child.on('error', (error) => reject(error));
+    child.on('close', (code, signal) => {
+      if (code === 0) {
+        resolve();
+      } else {
+        const reason = signal ? `signal ${signal}` : `exit code ${code}`;
+        reject(new Error(`Command failed (${reason}): ${command} ${args.join(' ')}`));
+      }
+    });
+  });
+}
+
+export async function ensureCliBuilt() {
+  if (existsSync(cliEntry)) {
+    return;
+  }
+
+  if (!buildPromise) {
+    buildPromise = runCommand('pnpm', ['run', 'build']).catch((error) => {
+      buildPromise = undefined;
+      throw error;
+    });
+  }
+
+  await buildPromise;
+
+  if (!existsSync(cliEntry)) {
+    throw new Error('CLI entry point missing after build. Expected dist/cli/index.js');
+  }
+}
+
+export async function runCLI(args: string[] = [], options: RunCLIOptions = {}): Promise<RunCLIResult> {
+  await ensureCliBuilt();
+
+  const finalArgs = Array.isArray(args) ? args : [args];
+  const invocation = [cliEntry, ...finalArgs].join(' ');
+
+  return new Promise<RunCLIResult>((resolve, reject) => {
+    const child = spawn(process.execPath, [cliEntry, ...finalArgs], {
+      cwd: options.cwd ?? projectRoot,
+      env: {
+        ...process.env,
+        OPEN_SPEC_INTERACTIVE: '0',
+        ...options.env,
+      },
+      stdio: ['pipe', 'pipe', 'pipe'],
+      windowsHide: true,
+    });
+
+    let stdout = '';
+    let stderr = '';
+    let timedOut = false;
+
+    const timeout = options.timeoutMs
+      ? setTimeout(() => {
+          timedOut = true;
+          child.kill('SIGKILL');
+        }, options.timeoutMs)
+      : undefined;
+
+    child.stdout?.setEncoding('utf-8');
+    child.stdout?.on('data', (chunk) => {
+      stdout += chunk;
+    });
+
+    child.stderr?.setEncoding('utf-8');
+    child.stderr?.on('data', (chunk) => {
+      stderr += chunk;
+    });
+
+    child.on('error', (error) => {
+      if (timeout) clearTimeout(timeout);
+      reject(error);
+    });
+
+    child.on('close', (code, signal) => {
+      if (timeout) clearTimeout(timeout);
+      resolve({
+        exitCode: code,
+        signal,
+        stdout,
+        stderr,
+        timedOut,
+        command: `node ${invocation}`,
+      });
+    });
+
+    if (options.input && child.stdin) {
+      child.stdin.end(options.input);
+    } else if (child.stdin) {
+      child.stdin.end();
+    }
+  });
+}
+
+export const cliProjectRoot = projectRoot;
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Tabish Bidiwale	e0be11dd85	Clarify release automation proposal	2025-10-02 00:54:14 +10:00
Tabish Bidiwale	9848242587	chore: add change proposals for agent scaffolding (#108 )	2025-10-02 00:26:25 +10:00
Tabish Bidiwale	5e0d21d1ed	chore: release 0.7.0 (#107 )	2025-10-01 23:01:23 +10:00
Tabish Bidiwale	31d85d0e8b	feat: Always install agentsmd (#106 ) * Update CLI init to install root agents * cleanup init command	2025-10-01 22:51:15 +10:00
Tabish Bidiwale	bc3666d702	feat: Add Kilo Code workflow support (#105 ) Implements Kilo Code integration with the following features: - Added Kilo Code as a selectable AI tool in `openspec init` - Created KiloCodeSlashCommandConfigurator to generate workflow files - Generates `.kilocode/workflows/openspec-{proposal,apply,archive}.md` - Added update support to refresh existing Kilo Code workflows - Updated README with Kilo Code integration details - Added comprehensive test coverage for init and update commands - Updated CHANGELOG with new feature All tasks from the change proposal are complete.	2025-10-01 19:01:10 +10:00
Tabish Bidiwale	970b9f6e2d	Add Kilo Code workflow proposal (#103 )	2025-10-01 13:21:22 +10:00
Tabish Bidiwale	5cb84a775e	Add change proposal for Windsurf workflow support (#94 ) * docs(windsurf): propose workflow support * restore missing opencode spec	2025-10-01 11:51:07 +10:00
Tabish Bidiwale	adc63069a9	chore(release): version packages (#100 )	2025-09-30 17:35:29 +10:00
Tabish Bidiwale	f8eca37796	feat(init): slim root agent instructions (#98 ) * feat(init): slim root agent instructions * Fix marker updates to ignore inline mentions * styling updates * update instructions * fix tests	2025-09-30 17:03:56 +10:00
Tabish Bidiwale	a908dc5a05	chore(release): version packages (#93 ) Bump version to 0.5.0 with new features and improvements: - E2E testing with cross-platform CI matrix - Improved apply instructions - Documentation improvements and cleanup	2025-09-29 23:47:22 +10:00
Tabish Bidiwale	b46f99b9bc	Make apply instructions more specific (#92 )	2025-09-29 23:41:24 +10:00
Tabish Bidiwale	6f7cc2abd2	archive completed changes (#91 )	2025-09-29 23:03:04 +10:00
Tabish Bidiwale	4867bfade5	feat: implement Phase 1 E2E testing with cross-platform CI matrix (#80 ) * feat: implement Phase 1 E2E testing with cross-platform CI matrix - Add shared runCLI helper in test/helpers/run-cli.ts for spawn testing - Create test/cli-e2e/basic.test.ts covering help, version, validate flows - Migrate existing CLI exec tests to use runCLI helper - Extend CI matrix to bash (Linux/macOS) and pwsh (Windows) - Update Phase 1 tasks and proposal with implementation status * fix: correct YAML syntax in CI workflow diagnostics command * fix: use multiline YAML for diagnostics command * fix ci * fix: ci * fix: update core validation and json converter * chore(ci): split pr and main workflows * refactor: simplify CI workflow with unified matrix strategy - Consolidate test_pr and test_matrix into single test job - Add proper shell configuration with defaults - Add timeout protection (15 minutes) - Simplify required-checks to single job - Maintain cross-platform testing (bash on Linux/macOS, pwsh on Windows) * fix: restore lean PR workflow with async main branch matrix - PRs run only essential tests on ubuntu-latest (fast feedback) - Main branch runs full cross-platform matrix asynchronously - Separate required-checks for each workflow type - Different timeouts: 10min for PR, 15min for matrix	2025-09-29 22:20:30 +10:00
Tabish Bidiwale	7359b4846a	docs(archive): document non-interactive flag (#90 )	2025-09-29 15:59:51 +10:00
Tabish Bidiwale	88526e6b93	docs(readme): replace discord badge (#87 )	2025-09-26 18:23:37 +10:00
Tabish Bidiwale	367aa12892	chore(release): version packages (#86 )	2025-09-26 16:03:15 +10:00
James G. Best	dcfb6afe0c	feat: add Opencode slash commands (#83 ) * First pass at adding Opencode slash commands * Fix the agent * Pass in Arguments to opencode slash commands * Remove unneeded agents file	2025-09-26 01:37:30 +10:00
Tabish Bidiwale	86925b2b2d	docs: add --yes flag to archive command template (#84 )	2025-09-26 00:32:56 +10:00
Tabish Bidiwale	604ecb8bd1	fix: normalize line endings in markdown parser to handle CRLF files (#79 ) Fixes validation errors on Windows by normalizing CRLF/CR line endings to LF before parsing sections. Adds comprehensive test coverage for CRLF handling in both unit and integration tests.	2025-09-25 15:59:09 +10:00
Tabish Bidiwale	5a4837c37d	feat: add OpenSpec change proposals for CLI improvements (#78 ) * feat: add CLI e2e testing improvement plan ## Summary - Add phased approach to stabilize CLI spawn testing - Expand cross-shell/OS matrix coverage when stable - Optional packaging validation for CI environments * feat: add markdown parser CRLF fix proposal and update e2e plan - Add comprehensive proposal for fixing CRLF parsing issues on Windows - Update CLI path references from dist/cli.js to dist/cli/index.js - Streamline e2e testing tasks based on refined approach * fix: correct spec delta to add parsing requirement instead of modifying remediation - Change from MODIFIED to ADDED Requirements for cross-platform line ending parsing - Create focused requirement for parser behavior rather than validation messages - Maintain logical coherence between requirement and scenario	2025-09-25 14:53:21 +10:00