mirror of https://github.com/anthropics/claude-plugins-official.git synced 2026-10-02 01:34:57 +08:00

T

dltn b6041c7721 imessage: surface every inbound image, not just the first

An iMessage with several photos arrived with only the first one in the
channel tag: handleInbound took the first image attachment and stopped.
Collect every image attachment instead (same filters as before) and pass
each path in the notification meta as image_path, image_path_2,
image_path_3, ... so the model can Read all of them. A single image still
produces exactly image_path, so existing behaviour is unchanged.

Numbered keys rather than an array or a joined list: Claude Code accepts
only string values in channel meta and renders each key as an attribute
on the <channel> tag, so keys must be plain identifiers; one key per path
also avoids inventing a delimiter for sender-controlled filenames. The
attachments query gains ORDER BY a.ROWID so the numbering follows
attachment ROWID (creation) order. Instructions and README updated to
match; version 0.1.0 -> 0.2.0 in plugin.json and package.json.

Known limits, unchanged by this patch: attachments still downloading
when the message row is first polled (filename NULL) are skipped and,
since the poll watermark has already passed the message, never picked up
later; HEIC is passed through unconverted; attachments with a NULL
mime_type still pass the image filter; no cap on images per message.

2026-09-30 15:34:53 -04:00

.claude-plugin

postman: repoint to postmanlabs/postman-plugin (#6326 )

2026-09-29 14:28:19 -07:00

.github

Exempt command sources from scope guard source.url check (#6296 )

2026-09-28 06:14:38 -07:00

external_plugins

imessage: surface every inbound image, not just the first

2026-09-30 15:34:53 -04:00

plugins

Merge pull request #6309 from anthropics/morganl/code-modernization-consolidated

2026-09-25 16:12:23 -07:00

.gitignore

…

LICENSE

…

README.md

feat: add renames map for auto-migration of renamed plugins (#3176 )

2026-07-03 19:17:44 -05:00

README.md

Claude Code Plugins Directory

A curated directory of high-quality plugins for Claude Code.

⚠️ Important: Make sure you trust a plugin before installing, updating, or using it. Anthropic does not control what MCP servers, files, or other software are included in plugins and cannot verify that they will work as intended or that they won't change. See each plugin's homepage for more information.

Structure

/plugins - Internal plugins developed and maintained by Anthropic
/external_plugins - Third-party plugins from partners and the community

Installation

Plugins can be installed directly from this marketplace via Claude Code's plugin system.

To install, run /plugin install {plugin-name}@claude-plugins-official

or browse for the plugin in /plugin > Discover

Contributing

Internal Plugins

Internal plugins are developed by Anthropic team members. See /plugins/example-plugin for a reference implementation.

External Plugins

Third-party partners can submit plugins for inclusion in the marketplace. External plugins must meet quality and security standards for approval. To submit a new plugin, use the plugin directory submission form.

Plugin Structure

Each plugin follows a standard structure:

plugin-name/
├── .claude-plugin/
│   └── plugin.json      # Plugin metadata (required)
├── .mcp.json            # MCP server configuration (optional)
├── commands/            # Slash commands (optional)
├── agents/              # Agent definitions (optional)
├── skills/              # Skill definitions (optional)
└── README.md            # Documentation

Plugin names are immutable

The name field in a marketplace entry is an immutable slug. Once a plugin has been published, its name must not change — users have it installed under that slug, and renaming it breaks their install with a plugin-not-found error.

To change how a plugin is labeled in the UI, set or update displayName instead.
If a rename is genuinely unavoidable, add an entry to the top-level renames map in .claude-plugin/marketplace.json so existing installs auto-migrate:

"renames": {
  "old-name": "new-name"
}

The Claude Code plugin loader reads this map and transparently rewrites the old slug to the new one on the user's next sync.

Skill-bundle plugins

When a plugin's source repository ships skills (SKILL.md files) without a .claude-plugin/plugin.json manifest, the marketplace entry can declare the skills directly using strict: false and an explicit skills array.

{
  "name": "example-bundle",
  "description": "Brief description of the bundled skills.",
  "author": { "name": "Author Name" },
  "category": "development",
  "source": {
    "source": "git-subdir",
    "url": "https://github.com/example-org/sdk.git",
    "path": "packages/agent-skills",
    "ref": "main",
    "sha": "<commit sha>"
  },
  "strict": false,
  "skills": [
    "./skill-a",
    "./skill-b",
    "./skill-c"
  ],
  "homepage": "https://github.com/example-org/sdk"
}

Each path in skills is relative to source.path and points at a directory containing a SKILL.md. Paths can reach deeper than a single level — for example, ["./libA/skill-1", "./libB/skill-2"] exposes a curated subset across multiple library subdirectories. Each skill is registered as <plugin-name>:<skill-name> in Claude Code.

For the underlying schema, see Strict mode in the marketplace documentation.

License

Please see each linked plugin for the relevant LICENSE file.

Documentation

For more information on developing Claude Code plugins, see the official documentation.