// List the Claude Code plugins currently enabled for the agent, read straight from settings.json.
| name | list-plugins |
| x-phantom-source | built-in |
| description | List the Claude Code plugins currently enabled for the agent, read straight from settings.json. |
| when_to_use | Use when the operator asks "what plugins are installed", "which plugins are active", "show plugins", "list plugins", "show me the marketplace state", or any narrow question specifically about the current plugin set. |
| allowed-tools | ["Read"] |
| context | inline |
Tell the operator which plugins are currently active for this agent, with their marketplace ids and a short description, in under 100 words.
Use Read on /home/phantom/.claude/settings.json. Parse it as JSON.
If the file does not exist, return: "No settings.json yet. The dashboard plugins tab is at /ui/dashboard/#/plugins."
If the file exists but has no enabledPlugins field, return: "No plugins enabled yet. Browse the marketplace at /ui/dashboard/#/plugins."
Success criteria: you have either a parsed enabledPlugins map or a clear empty-state message ready.
For each key: value in enabledPlugins, treat the entry as active when value is true, a non-empty array, or a non-empty object. Treat false and missing entries as inactive.
Success criteria: you have a list of plugin@marketplace keys for active plugins only.
Format the response like this:
You have N plugins enabled:
- linear at claude-plugins-official - Linear issue tracking
- notion at claude-plugins-official - Notion workspace
- slack at claude-plugins-official - Slack workspace messages
- claude-md-management at claude-plugins-official - CLAUDE.md maintenance
Manage plugins at /ui/dashboard/#/plugins.
For each row, the descriptor after the dash is a short fallback string based on the plugin name. If you do not recognize a plugin id, use just the marketplace id as the descriptor.
Success criteria: the response shows the real current keys, the descriptors are honest (no fabricated descriptions for unknown plugins), and the dashboard URL is included.
List the agent's current skills, memory files, plugins, subagents, hooks, and a settings summary plus dashboard URLs. The user-facing discovery path for everything the operator can edit.
Before answering a substantive question, quietly check whether the user has already resolved this question in the past.
Weekly self-audit playback. Surface patterns from the user's past week that they probably cannot see themselves.
Find commitments the user made in the last two weeks and did not follow through on. A promises audit.
Discover recurring behaviors from memory and offer to formalize them as scheduled jobs.
Show how the user's thinking on a specific topic has evolved over time. A chronological narrative with turning-point callouts.
