Item detail

stevesolun/ctx

stevesolun/ctx is an MIT-licensed, open-source skill, agent, MCP, and harness recommender for Claude Code and custom LLMs that walks a 79,958-node knowledge graph of 68,494 skill entity pages, 467 agents, 10,790 MCP servers, and 207 harnesses to recommend a small, top-scored bundle for the current task, with dry-run, update, and uninstall controls, so AI coding agent builders and power-user develo

Score7.9
Popularity8.1
Risklow
TierSilver
Score breakdown
Usefulness7.0
Novelty9.0
Momentum7.0
Maturity5.9
Open-source/build8.4
Evidence7.2
Workflow potential8.7
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI coding agent builders, power-user developers, and Claude Code power users who need an MIT-licensed, open-source skill, agent, MCP, and harness recommender for Claude Code and custom LLMs that walks a 79,958-node knowledge graph of 68,494 skill entity pages, 467 agents, 10,790 MCP servers, and 207 harnesses to recommend a small, top-scored bundle for the current task, with dry-run, up

Who should use it

AI coding agent builders who need an MIT-licensed, open-source skill, agent, MCP, and harness recommender that walks a 79,958-node knowledge graph to recommend a small, top-scored bundle for the current taskpower-user developers who want a single CLI that recommends the right skills, agents, and MCP servers for a project without manually scanning thousands of optionsClaude Code power users who need a custom-LLM harness setup flow with dry-run, update, and uninstall controlsopen-source contributors who want an MIT-licensed alternative to single-ecosystem skill and MCP registries

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

It is an MIT-licensed skill, agent, MCP, and harness recommender that walks a 79,958-node knowledge graph, so review which skills, agents, and MCP servers it recommends, scope which projects the recommender is allowed to scan, confirm that dry-run and uninstall controls are exercised before any install, and gate any production rollout behind a review pass before enabling ctx on shared developer machines.

Evidence links

Closest alternatives / related signals

skill-recommenderagent-recommendermcp-recommenderharnessclaude-codeknowledge-graphllm-wikiopen-source