How do I install the Brooks Sweep skill?

Run npx skillmds@latest add gabrielmoreira/brooks-sweep in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Brooks Sweep safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Brooks Sweep?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Brooks Sweep free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Brooks Sweep?

gabrielmoreira (@gabrielmoreira) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Brooks Sweep by gabrielmoreira — Agent Skill

Name: Brooks Sweep
Rating: 4.5 (4 reviews)
Author: gabrielmoreira

Brooks Sweep

Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.

gabrielmoreira Updated Sep 9, 2026 17 repo stars

File contents

Brooks-Lint — Full Sweep & Auto-Fix

Setup

Read in order:

../_shared/common.md — Iron Law, Project Config, Report Template, Health Score
../_shared/source-coverage.md — book coverage, exceptions, tradeoffs
../_shared/decay-risks.md — production risk symptoms
../_shared/test-decay-risks.md — test risk symptoms
sweep-guide.md (this directory) — the unified scan and fix process

Process

Scope: if the user did not specify a project or directory, apply Auto Scope Detection (../_shared/common.md) first.

Show the pre-flight consent notice and wait for one-time approval (Step 0 of the guide)
Enumerate scope and initialize pipeline state (Step 1 of the guide)
Run the four dimensions in sequence — review, test, debt, audit — each scanning, classifying, fixing, and verifying (Steps 2–5 of the guide)
Iterate over modified files and their consumers until a clean round or the cap (Step 6 of the guide)
Aggregate residual and unresolvable items and output the Full Sweep Report (Steps 7–8 of the guide)

Mode line in report: Full Sweep

---name: brooks-sweepdescription: Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user wants to "fix everything", "sweep the codebase", "auto-fix all issues", "clean up the whole project", or asks for a single command that both diagnoses and remediates quality problems. Do NOT trigger for: read-only audits or health reports where the user only wants findings without code changes; single-dimension reviews (use the focused skill instead: brooks-review / brooks-audit / brooks-debt / brooks-test); server health checks, HTTP /health endpoints, Kubernetes probes, database health, or application uptime.--- # Brooks-Lint — Full Sweep & Auto-Fix ## Setup Read in order: 1. `../_shared/common.md` — Iron Law, Project Config, Report Template, Health Score 2. `../_shared/source-coverage.md` — book coverage, exceptions, tradeoffs 3. `../_shared/decay-risks.md` — production risk symptoms 4. `../_shared/test-decay-risks.md` — test risk symptoms 5. `sweep-guide.md` (this directory) — the unified scan and fix process ## Process **Scope:** if the user did not specify a project or directory, apply Auto Scope Detection (`../_shared/common.md`) first. 1. Show the pre-flight consent notice and wait for one-time approval (Step 0 of the guide) 2. Enumerate scope and initialize pipeline state (Step 1 of the guide) 3. Run the four dimensions in sequence — review, test, debt, audit — each scanning, classifying, fixing, and verifying (Steps 2–5 of the guide) 4. Iterate over modified files and their consumers until a clean round or the cap (Step 6 of the guide) 5. Aggregate residual and unresolvable items and output the Full Sweep Report (Steps 7–8 of the guide) **Mode line in report:** `Full Sweep`

Frequently asked questions