charmbracelet/crush
GitHubGlamourous agentic coding for all 💘
- Stars:
- 28.9k
- Language:
- Go
- Default branch:
- main
- Last scored:
77.3
Overall
At a glance
- Rank
- #96 of 401
- Top 24% · #14 of 40 Go repos
- Checks passed
- 8 of 17
- Full list below
- Best set up for
- Pi
- Score 83.3
- Needs most work for
- OpenHands
- Biggest fix: .openhands/setup.sh (+10.0 pts)
What it has
What it's missing
What to fix first
Showing fixes for Claude Code
- 1CONTRIBUTING guideAdd CONTRIBUTING.md describing branch naming, commit style, test commands, and the PR process.+5.3 pts
- 2Pre-commit / git hooksSet up pre-commit (.pre-commit-config.yaml), husky, or lefthook to run format+lint on every commit.+5.3 pts
- 3Test suiteAdd a tests/ (or test/, __tests__/, spec/) directory with runnable tests. Document how to run them in AGENTS.md.+3.9 pts
Score for each AI agent
Each agent weighs the checks by its own docs. Under each score are its top three. How each agent is scored →
Does charmbracelet/crush have agent instructions?
An AGENTS.md (or CLAUDE.md) at the root tells AI coding agents how to build, test and work in the repo. A few agents also read a file of their own.
- AGENTS.md / CLAUDE.md
AGENTS.md(new tab) · 10,966 characters- Agent-specific files
.agents/skills(new tab) (2 skills)No GEMINI.md, .cursor/rules, .openhands/setup.sh or .aider.conf.yml- Repos that have one
- 23 of 40 Go repos · 221 of 401 repos on the leaderboard · See examples →
All 17 checks · 8 passed
✓
Skills (.agents/skills)· 100% pass
2 skills in .agents/skills/
✓
✗
.aider.conf.yml· 0% pass
No .aider.conf.yml at repo root
✓
✗
CONTRIBUTING guide· 0% pass
No CONTRIBUTING file
✗
Cursor rules (.cursor/rules)· 0% pass
No .cursor/rules/*.mdc or .cursorrules
✓
~
✗
GEMINI.md· 0% pass
No GEMINI.md at repo root
✓
✓
✗
.openhands/setup.sh· 0% pass
No .openhands/setup.sh
✗
Pre-commit / git hooks· 0% pass
No pre-commit / husky / lefthook found
~
Manageable size· 80% pass
1347 files
~
Test suite· 70% pass
Test files detected (internal/agent/accepted_run_test.go)
✓
Type configuration· 100% pass
Typed language (Go)
How charmbracelet/crush compares
- vs leaderboard average
- 10.5 pts above
- Average 66.8
- vs Go average
- 6.3 pts above
- Average 71.0
- Stars among Go repos
- #26 of 40
Missing here, and how many repos have it
- CONTRIBUTING guide · passed by 86% of leaderboard repos, 88% of Go repos
- Pre-commit / git hooks · passed by 29% of leaderboard repos, 13% of Go repos
- Cursor rules (.cursor/rules) · passed by 4% of leaderboard repos, 0% of Go repos
Passes checks most repos miss
- Skills (.agents/skills) · only 17% of repos pass it
One fix for the most agents: CONTRIBUTING guide would raise the score for all 9 agents, by up to 7.0 points.
Similar repos
Same language and host as this repo, closest in overall score.
- traefik/traefik79.4Go · 65.5k ★
- Go · 11.4k ★
- moby/moby77.5Go · 72.2k ★
- Go · 78.7k ★
- Go · 21k ★
- ollama/ollama76.7Go · 185.9k ★
Same topics, any language
Repos tagged with the same GitHub topics, most shared first.
- Python · agentic ai, LLM
- milvus-io/milvus85.9Go · LLM
- BerriAI/litellm85.2Python · LLM
- mastra-ai/mastra84.4TypeScript · LLM
- TypeScript · LLM
- QwenLM/qwen-code82.6TypeScript · LLM
Add a badge to your README
Paste this at the top of the README. It shows the score, and links back to this page.
[](https://agentfriendlycode.com/repo/github/charmbracelet/crush)Check the score on every pull request
A GitHub Action posts one comment per pull request with how the score changed and why.