#318 · Primary category： AI Coding Assistants
brooks-lint
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
Project last updated：08/24/26
GitHub Stars
1.4K
Forks
64
Contributors
5
License
MIT
Why we included this project
Most linters stop at syntax and cyclomatic complexity. brooks-lint targets the slower problems that age a codebase: architectural drift, knowledge duplication, and domain distortion. It runs as a Claude Code plugin, a Codex CLI skill, or a Gemini CLI extension, and you trigger reviews with slash commands like /brooks-review or /brooks-audit rather than wiring up a separate pipeline. Each finding comes back as a Symptom → Source → Consequence → Remedy block with a citation to one of twelve classic engineering books and a 0 to 100 health score, so you can see where the judgment came from and act on it. For PR review and architecture audits, the six decay risks and the full-sweep auto-fix mode give you a second opinion based on established practice.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.