autonomous-ai-agency: Skill for Claude Code

.agents/skills/git-hygiene/SKILL.md

git-hygiene is a skill for Claude Code, Codex from strikersam/autonomous-ai-agency. It costs 0 tokens per session (490 once invoked), scanned A, original, MIT.

A checklist for keeping a Git repository's changes, branches, history, and commit messages orderly. A commit is a saved group of code changes, while a branch is a separate line of work.

In plain words
What is it for?
Use it before opening a pull request, pushing to the main branch, or preparing a release. It reviews changes and recent commits and can clean up history when needed.
Why use it?
It helps catch unwanted files, secrets, unclear commit messages, and messy history before code is pushed or merged.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is strikersam/autonomous-ai-agency's own configuration. It tells Claude Code and Codex how to work on autonomous-ai-agency itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything autonomous-ai-agency configures →

Reuse

Borrowing it

Nothing to install: this file belongs to strikersam/autonomous-ai-agency. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/strikersam/autonomous-ai-agency/master/.agents/skills/git-hygiene/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/strikersam/autonomous-ai-agency

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for git-hygiene

README.md
[![agentmods](https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/git-hygiene/github.svg)](https://agentmods.dev/skills/strikersam/autonomous-ai-agency/git-hygiene)
Your own site
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/git-hygiene"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/git-hygiene/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.

agentmods 80×15 button for git-hygiene

Your own site · 80×15
<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/git-hygiene"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/git-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 490 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00490
Opus 5 $0.00000 $0.00245
Sonnet 5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 12d ago against content hash d2aacc93d9f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

git-hygiene 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 12d 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.

.agents/skills/git-hygiene/SKILL.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Git Hygiene

Purpose

Ensures the repository's git history, branch state, and commit messages are clean, meaningful, and follow project conventions before pushing or merging.

When to Use

  • Before pushing commits to master or opening a PR
  • When git history has become messy (fixup commits, WIP messages, etc.)
  • As a final step in any implementation workflow
  • When the changelog-enforcer or release-readiness skills are applied

Process

1. Review Staged and Unstaged Changes

  • Run git status to see what's changed
  • Confirm no unintended files are staged (build artifacts, secrets, editor files)
  • Check .gitignore is catching what it should

2. Review Commit History

  • Run git log --oneline -20 to inspect recent commits
  • Flag commits with vague messages: "fix", "wip", "test", "asdf", etc.
  • Note commits that could be squashed without losing meaning

3. Validate Commit Messages

  • Ensure messages follow the pattern: <type>: <short description> [#issue]
  • Valid types: feat, fix, docs, chore, refactor, test, style
  • Subject line should be ≤72 characters
  • No trailing periods in subject line

4. Clean Up if Needed

  • Squash fixup commits with git rebase -i if appropriate
  • Amend the most recent commit message with git commit --amend if needed
  • Do not rewrite history on shared branches unless explicitly authorized

5. Confirm Branch State

  • Ensure the working branch is up to date with its upstream
  • Resolve any merge conflicts before pushing
  • Confirm you are on the intended branch

6. Push

  • Push with git push origin <branch>
  • Use --force-with-lease only if a rebase was performed, never --force

Output

  • Clean git history with meaningful commit messages
  • No unintended files committed
  • Successful push to the correct branch

Notes

  • Never commit secrets, credentials, or API keys
  • Binary files and generated files should generally not be committed
  • If in doubt about a commit, use git diff HEAD~1 to review what it contains

Read the full file on GitHub · 53 lines

Changes

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.

  1. 12d ago First seen · 53 lines · 0 tokens per session scan A d2aacc93d9f4

Subscribe to this mod's changes

git-hygiene is a skill published in the GitHub repository strikersam/autonomous-ai-agency (8 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 490 tokens. 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.