#136136th of 324 in Skills, plugins and prompts
brooks-lint
Code review skills that cite classic engineering books for each finding
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 1.6k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- HTML
16 on 3 Apr 20261,554 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
brooks-lint is a set of Agent Skills and a Claude Code plugin that reviews code against six production decay risks and six test-suite decay risks drawn from twelve engineering books. Each finding is reported as Symptom, Source, Consequence, Remedy with a severity and a 0–100 Health Score. It provides six commands (review, audit, debt, test, health, sweep) and optional SARIF export and CI gates.
Who it is for: Developers using coding agents who want cited code and architecture reviews
Strengths
- Every finding carries a book citation, severity label and concrete remedy
- Installs on Claude Code, Codex, Gemini, Cursor, Windsurf, Copilot and others
- Per-project .brooks-lint.yaml sets strictness, disabled risks, ignores and custom risks
- Parser benchmark is reproducible locally with npm run benchmark on a frozen 30-report corpus
Weaknesses
- Review quality depends on the host LLM; live evals need an Anthropic API key
- Maintainer says only Codex is tested going forward; other platforms are unverified
- Headline benchmark table is described as illustrative and compares against plain Claude
- Does not check syntax or style; it complements a linter rather than replacing it
What it needs
- no GPU
- Needs Claude Code, Codex CLI or another Agent Skills host, ANTHROPIC_API_KEY (live evals only)
- Models: Claude, Codex, Gemini
Quick answers
Is brooks-lint open source?
Yes. Its code is on GitHub under the MIT license.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |