Build one deterministic Codewhale-owned bundle inventory with versioned manifests, contained content hashing, separate trust and enablement receipts, and fail-closed atomic state. Activate only namespaced Skills and MCP through their existing engines, initialize the registry consistently across launch modes, preserve legacy executable tools as a separate surface, and document the bounded v0.9.1 lifecycle. Refs #4399, #3916, #3917. Builds on the original plugin manifest, discovery, CLI, and MCP foundation from pkeging in #3708, #3709, and #3710. Co-authored-by: pkeging <237035657+pkeging@users.noreply.github.com> Signed-off-by: Hunter B <hmbown@gmail.com>
1.8 KiB
Claude Plugin Compatibility
Codewhale treats Claude Code skill folders as instruction bundles when they are
plain SKILL.md directories. It does not run Claude Code plugin runtimes.
Supported
- Workspace or global
.claude/skills/<name>/SKILL.mddirectories discovered by the normal skill registry. - GitHub or tarball installs that contain one selected skill directory such as
skills/<name>/SKILL.md,.agents/skills/<name>/SKILL.md,.claude/skills/<name>/SKILL.md, or a nested package layout ending inskills/<name>/SKILL.md. - Companion files inside the selected skill directory, such as
references/,examples/, or scripts that are only used after the skill is explicitly loaded and trusted.
Not Supported As A Plugin Runtime
Claude Code plugin features remain outside the compatibility boundary:
.claude-plugin/plugin.jsonmetadata and activation semantics.- Custom slash-command bundles.
- Plugin build steps, compiled TypeScript agents, dashboard servers, shared plugin state, or token-gated service processes.
- Frontmatter fields that require Claude-specific runtime behavior, such as
model: inherit.
If a Claude Code plugin repository contains multiple skills, install or migrate
one skills/<name> directory at a time. /skill install rejects multi-skill
plugin archives with a clear message so it never silently chooses one skill and
drops the plugin runtime behavior.
For richer integrations, wrap the plugin's executable surface as MCP, hooks, or a Codewhale skill that names the external command explicitly.
Codewhale's own versioned plugin bundles are a different, explicitly trusted
format. v0.9.1 can activate namespaced Skills and MCP configuration from
plugin.toml, but it does not scan, convert, install, or trust Claude bundles
automatically. See PLUGIN_BUNDLES.md.