claude-ctx 0.5.0rc3

Skill and agent recommendation system for Claude Code — knowledge graph, wiki, and intake quality gates

ctx — Skill & Agent Recommendation for Claude Code

Watches what you develop, walks a knowledge graph of 1,768 skills and 443 agents, and recommends the right ones on the fly — you decide what to load and unload. Powered by a Karpathy LLM wiki with persistent memory that gets smarter every session.

Why it exists

• Discovery — with 1,700+ skills and 400+ agents, you can't possibly know which exist or which apply to your current repo.
• Context budget — loading everything wastes tokens and degrades quality. You need the right 10–15 per session.
• Skill rot — skills you installed months ago and never used are cluttering context. Stale ones should be flagged automatically.

Install

pip install claude-ctx

That's it. Optional extras: pip install "claude-ctx[embeddings]" for the semantic backend, pip install "claude-ctx[dev]" for the test toolchain.

Use

After install, the ctx hooks integrate automatically with Claude Code's PostToolUse + Stop events. Typical flow:

ctx-scan-repo              # scan current repo, surface recommended skills/agents
ctx-skill-quality list     # see the four-signal quality score for every skill
ctx-skill-quality explain python-patterns   # drill into a single skill
ctx-skill-health dashboard # structural health + drift detection
ctx-toolbox run review     # run a council of skills + agents on the current diff

Full docs, architecture, and every module: https://stevesolun.github.io/ctx/

License

MIT — see LICENSE.