skillreaper

v0.8.0

Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.

Claude Code2 Skills

By thousandflowersLicense: MIT54 GitHub starsUpdated 2 hours ago

Directory evidence

Runtimes: Claude Code
Parsed components: 2 skill or MCP entries
Source updated: Aug 30, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install skillreaper for Claude Code

Installs for the current user

claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install skillreaper@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/thousandflowers/skillreaper

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/skillreaper/.

Plugin files

plugins/skillreaper/

├── .claude-plugin/plugin.json
├── skills/gap/SKILL.md
└── skills/reap/SKILL.md

Included Skills2

gapskills/gap/SKILL.md

Measure the loaded-versus-fired gap - what fraction of each category of loaded context is ever actually invoked, and which MCP tools return mostly noise. Use when asked how much of the context is earning its place, or which categories are worst.

reapskills/reap/SKILL.md

Report how much of the context this agent loads is never used - unused skills, MCP servers, subagents, hooks and always-loaded prose - measured from real session transcripts. Use when asked why the context window is full, what is wasting tokens, or what is safe to remove.

Plugin manifests1

plugins/skillreaper/.claude-plugin/plugin.json

{
  "name": "skillreaper",
  "displayName": "skillreaper",
  "description": "Measures what share of your agent's loaded context is ever actually invoked - skills, MCP servers, subagents, hooks, always-loaded prose - using evidence from your own session transcripts. Then prunes the dead weight, reversibly.",
  "version": "0.8.0",
  "author": {
    "name": "thousandflowers",
    "url": "https://github.com/thousandflowers"
  },
  "homepage": "https://github.com/thousandflowers/skillreaper",
  "repository": "https://github.com/thousandflowers/skillreaper",
  "license": "MIT",
  "keywords": [
    "unused-skills",
    "context-window",
    "token-waste",
    "utilization",
    "mcp",
    "subagents",
    "hooks",
    "pruning",
    "measurement"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[skillreaper on Agent Plugins Marketplace](https://pluginsmp.com/plugins/skillreaper)