chenglou/pretextGitHub
https://github.com/chenglou/pretext- Stars:
- 45.2k
- Default branch:
- main
- Last scored:
- 4h ago
73.5
Overall
Strengths
- AGENTS.md / CLAUDE.md
- CI configuration
- Dependency manifest
- License file
- README
Gaps
- CONTRIBUTING guide
- Linter / formatter config
- Pre-commit / git hooks
Suggestions to improve for a specific model
- 1CONTRIBUTING guideAdd CONTRIBUTING.md describing branch naming, commit style, test commands, and the PR process.+6.3 pts
- 2Linter / formatter configConfigure a linter/formatter (ESLint+Prettier, Biome, Ruff, rustfmt+clippy, golangci-lint) and commit the config.+6.3 pts
- 3Pre-commit / git hooksSet up pre-commit (.pre-commit-config.yaml), husky, or lefthook to run format+lint on every commit.+6.3 pts
Per-model scores
Claude Code
Weights AGENTS.md and tests heavily — Claude Code leans on an instructions file and a fast feedback loop.
Cursor
Weights type config and a detailed README highly — Cursor's inline edits benefit from static types and skim-readable docs.
Devin
Weights CI and reproducible envs highly — Devin runs in a sandboxed VM and needs end-to-end automation.
GPT-5 Codex
Balanced profile as a reference point.
Signal breakdown
AGENTS.md / CLAUDE.md· 100% pass
Substantive (17264 chars)
AGENTS.md
CI configuration· 100% pass
1 GitHub Actions workflow(s)
.github/workflows
CONTRIBUTING guide· 0% pass
No CONTRIBUTING file
Dependency manifest· 100% pass
Manifest present
package.json
Reproducible dev env· 60% pass
package.json has 32 scripts
package.json
License file· 100% pass
License present
LICENSE
Linter / formatter config· 0% pass
No linter/formatter config found
Pre-commit / git hooks· 0% pass
No pre-commit / husky / lefthook found
README· 100% pass
README detailed (16724 chars)
README.md
Manageable size· 100% pass
123 files
Test suite· 70% pass
Test files detected (src/layout.test.ts)
src/layout.test.ts
Type configuration· 100% pass
Type config present
tsconfig.json