Stats
Actions
Tags
From brooks-lint
Runs a unified analysis across code decay, architecture, tech debt, and test quality, then applies fixes automatically (safe changes) or with confirmation (risky changes).
How this skill is triggered — by the user, by Claude, or both
Slash command
/brooks-lint:brooks-sweepThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
1. Read `../_shared/common.md` for the Iron Law, Project Config, Report Template, and Health Score rules
../_shared/common.md for the Iron Law, Project Config, Report Template, and Health Score rules../_shared/source-coverage.md for book-level coverage, exceptions, and tradeoffs../_shared/decay-risks.md for production risk symptom definitions../_shared/test-decay-risks.md for test risk symptom definitionssweep-guide.md in this directory for the unified scan and fix processIf the user has not specified a project or directory: apply Auto Scope Detection
from ../_shared/common.md to determine the review scope before proceeding.
unresolvable / non_critical_rounds / fix_log state (Step 1 of the guide)unresolvable set, cap non-critical rounds at 3 (Step 6 of the guide)Mode line in report: Full Sweep
npx claudepluginhub hyhmrright/brooks-lint --plugin brooks-lintReviews PRs and code for decay risks, design smells, and maintainability issues using Symptom → Source → Consequence → Remedy findings from twelve classic engineering books.
Analyzes code quality via cleanup analysis for technical debt and multi-perspective reviews with explicit fix/defer/reject decisions.
Performs repo-wide or PR diff readiness sweeps dispatching parallel agents across security (shieldkit), tests (testkit), codebase (lenskit), evolution (timewarp), and instructions (alignkit) for synthesized reports.