Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add gg-mo/repo-hygiene --skill cleaning-existing-codebasegit clone --depth 1 https://github.com/gg-mo/repo-hygieneWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gg-mo/repo-hygiene/cleaning-existing-codebase)<a href="https://agentmods.dev/skills/gg-mo/repo-hygiene/cleaning-existing-codebase"><img src="https://agentmods.dev/badge/skills/gg-mo/repo-hygiene/cleaning-existing-codebase/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gg-mo/repo-hygiene/cleaning-existing-codebase"><img src="https://agentmods.dev/badge/skills/gg-mo/repo-hygiene/cleaning-existing-codebase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01144 |
| Opus 5 | $0.00030 | $0.00572 |
| Sonnet 5 | $0.00012 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
cleaning-existing-codebase scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cleaning an Existing Codebase
Overview
When a user asks to apply hygiene to an existing project, the seductive path is to start with the visible, mechanical work — docstrings on every file, README rewrite, dep pruning — and ship a 200-file diff. That optimizes for appearing thorough; it does NOT optimize for being useful. The god-class is usually the real liability; everything else is decoration.
Core principle: Survey, propose, get buy-in, work in small reviewable phases. Don't type any cleanup code until the user has approved a plan.
When To Use
- User asks to "clean up" / "apply repo-hygiene" / "fix the hygiene of" an existing project
- Onboarding into a long-running codebase with obvious hygiene debt
- Tech-debt sprint where hygiene is the focus
The Process
1. Survey
Invoke repo-hygiene:orienting-to-repo first. Then quantify the hygiene gaps with concrete numbers:
- File-size offenders — files >500 lines, ranked.
find . -type f \( -name '*.py' -o -name '*.ts' -o -name '*.go' \) -exec wc -l {} + | sort -rn | head -20 - Docstring coverage — sample 10 random functions across the codebase; how many have useful docstrings?
- Test coverage — count test files vs source files. Run the suite if possible; capture pass rate and gaps.
- Stale docs —
git log -1 --format=%cs README.md CHANGELOG.md; spot-check the README against current code - Dead-code candidates — unused imports, unreferenced exports. Don't act yet; just note.
- Dep hygiene — unused deps in
requirements.txt/package.json
Output a concise inventory (~10 bullets with numbers). NOT a 5-page audit.
2. Propose a Phased Plan
Show the plan to the user BEFORE touching code. Default ordering, by leverage and dependency:
| Phase | Why this position |
|---|---|
| 0 — Safety net | Add a smoke test or characterization test for the biggest module BEFORE any refactor. Refactoring without tests is reckless. |
| 1 — Cheap visibility wins | Fix README, prune unused deps, add CHANGELOG entry. Reviewable in minutes; signals progress. |
| 2 — Architecture | Decompose god-files / god-classes. Highest risk; needs Phase 0 done first. |
| 3 — Documentation sweep | Docstrings across files. Last, so docs describe the SHAPE AFTER restructuring, not the moving target. |
| 4 — Test backfill | Coverage floor on changed code. Use repo-hygiene:testing-new-code per file. |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 88 lines · 59 tokens per session scan A b2565106f96e
cleaning-existing-codebase is a skill published in the GitHub repository gg-mo/repo-hygiene (3 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,144 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-audit
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized…
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…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…