ccam-config — Claude Code plugin: what it does, how to install
ccam-config audits a Claude setup and its per-project memory: duplicated skills, risky hooks, stale facts. Results land in the dashboard at http://localhost:4820.
MIT ★ 1,198 updated 2026-10-23
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor
/plugin install ccam-config@claude-code-agent-monitor-pluginsWhat ccam-config does
Point it at a Claude setup and it inventories what's actually wired up: skills, subagents, slash commands, MCP servers, hooks, settings, and the memory store each project keeps. Copy-paste and sprawl surface fast.
Reads go through the Agent Monitor Config Explorer API, and the output lives in the dashboard at http://localhost:4820. No monitor running there means nothing to inspect.
The audit names hooks that deserve a second look before your next run, and stale entries still sitting in file-based memory. Old notes age badly, and the agent keeps trusting them until someone removes them.
What it helps with
- spot duplicate skills and subagents across projects
- flag hooks that look risky
- prune stale facts from the project memory store
- list every MCP server and slash command in one view
- compare settings between projects
Example prompts for the agent
- Show me which hooks in my config look risky
- Find duplicate skills and subagents in this project
- What's stale in the project memory store? Run it through Config Explorer
How to install ccam-config
Plugin marketplace
/plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor/plugin install ccam-config@claude-code-agent-monitor-pluginsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about ccam-config
How do I install ccam-config in Claude Code?
Add the marketplace with /plugin marketplace add hoangsonww/Claude-Code-Agent-Monitor, then install the plugin: /plugin install ccam-config@claude-code-agent-monitor-plugins.
What does ccam-config do?
It audits Claude configuration and file-based memory: skills, subagents, commands, MCP servers, hooks and settings. The report shows duplication, sprawl and risky hooks.
Where do I see the audit results?
In the Agent Monitor dashboard at http://localhost:4820, which serves the data through its Config Explorer API.
Source text
ccam-config · MIT
Audit and govern your Claude Code configuration and file-based memory via the Agent Monitor Config Explorer API — skills, subagents, commands, MCP servers, hooks, settings, and the per-project memory store. Surfaces sprawl, duplication, risky hooks, and stale facts, all read through the dashboard at http://localhost:4820.
© Son Nguyen · MIT · hoangsonww/Claude-Code-Agent-Monitor