brooks-lint
Code review grounded in classic engineering books: findings with source citations, severity labels and several analysis modes
Medium risk
We rate an entry medium when the tool runs code, makes network calls or reads project files. Check what exactly it does before installing.
Why this level
- Reads code files for review
- Changes files in auto-fix mode
Install
In your terminal, with SkillFoxx CLI
npx skillfoxx add plugins/brooks-lintDetects the agents on your machine, checks the risk and pins the version.
Other ways to install
Run one by one in the Claude Code chat
/plugin marketplace add hyhmrright/brooks-lint
/plugin install brooks-lint@brooks-lint-marketplaceInstall the plugin: /plugin marketplace add hyhmrright/brooks-lint, then /plugin install brooks-lint@brooks-lint-marketplace.
Other ways from the author
/plugin marketplace add hyhmrright/brooks-lint
/plugin install brooks-lint@brooks-lint-marketplaceThis is third-party code. Review the repository files before installing.
What it does
brooks-lint lets the agent review code against principles from a dozen classic software books. Each finding comes with a book citation, a severity label and an explanation of the decay risk. It has several modes, from a focused pass to a full sweep with automatic fixes. It installs as a plugin in Claude Code and Codex or via an install script for other skill-based platforms.
Who it is for. For developers and reviewers who want code review with reasoning rather than a bare list of remarks.
Good fit when
- You want review that explains why something is a problem
- You want a shared quality bar with source citations
- You need a full sweep with suggested fixes
Not a fit when
- You need a plain syntax-level static linter
- You cannot let the agent change code in auto-fix mode
Example request
Review this module with brooks-lint and show findings with book citations and severityLimitations
Review quality depends on the model reading the code, so results vary between runs. The auto-fix mode changes files, so use it on version-controlled code.
How to disable. Remove the brooks-lint plugin via /plugin or delete the copied skills from your agent's skills directory.
Security check
- Reads code files for review
- Changes files in auto-fix mode
README in short
The README describes brooks-lint as code review based on classic software books, with findings, citations, severity labels and six analysis modes. It installs as a plugin in Claude Code and Codex or via an install.sh script for many skill-based platforms, with manual copying into the skills directory. It also documents benchmarks: parsing a frozen report corpus and a scenario eval suite. It lists skills directories for various agents.
FAQ
What are the remarks based on?
On principles from a set of classic engineering books; each finding carries a citation.
Is there auto-fix?
Yes, one of the modes is a full sweep with automatic fixes.
Related
A skills library that gives coding agents a development process: brainstorming, planning, TDD, subagents and code review
Skills for real engineers by Matt Pocock
Skills For Real Engineers
Small composable skills for engineering with agents: plan grilling, TDD, bug diagnosis, code review and architecture
GitHub toolkit for spec-driven development: the specify CLI adds agent commands and skills to a project, from principles to implementation
Reference MCP servers
Model Context Protocol servers
Official reference MCP servers: Filesystem, Fetch, Git, Memory, Sequential Thinking, Time and Everything