Using Repo Hygiene
Use when starting any conversation in a repo — establishes the repo-hygiene skill set and the moments each sub-skill applies
Install
$ agentstack add skill-gg-mo-repo-hygiene-using-repo-hygiene ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-gg-mo-repo-hygiene-using-repo-hygiene) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
If you were dispatched as a subagent to execute a specific task, skip this skill.
Using Repo Hygiene
This plugin keeps a codebase healthy as you work in it. Each sub-skill triggers on a specific moment — invoke it then via the Skill tool.
Important override: This skill set INVERTS the usual "no comments unless WHY is non-obvious" default. In a repo using this plugin, docstrings on functions and file headers ARE expected. Quality matters (see repo-hygiene:writing-docstrings); silence does not.
Trigger Table
| When this happens | Invoke | |---|---| | Starting substantive work in a repo you don't already understand | repo-hygiene:orienting-to-repo | | Writing or modifying a function, class, or source file | repo-hygiene:writing-docstrings | | About to add lines to a file >400 lines, or your edit pushes one past that | repo-hygiene:keeping-files-small | | Changing a public API (renamed export, new flag, new route, changed signature) | repo-hygiene:keeping-docs-fresh | | Adding business logic, branching code, or fixing a bug | repo-hygiene:testing-new-code | | Drafting any commit message | repo-hygiene:writing-commit-messages | | User asks to commit, merge, or push | repo-hygiene:gating-commits | | User asks to "clean up" or apply repo-hygiene to an existing codebase | repo-hygiene:cleaning-existing-codebase |
Priority
- User instructions win. If the user says "skip the orientation," skip it.
- Coordinate with peer skill sets. If
superpowers:test-driven-developmentis already in play,testing-new-codeis satisfied by that workflow. - Otherwise apply at the triggers above.
Bypass
A user can bypass a hygiene skill for one turn with #hygiene-skip in their message. Acknowledge the bypass and proceed.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: gg-mo
- Source: gg-mo/repo-hygiene
- License: MIT
- Homepage: https://github.com/gg-mo/repo-hygiene
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.