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 alexei-led/cc-thingz --skill configuring-git-hygienegit clone --depth 1 https://github.com/alexei-led/cc-thingzWrote 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/alexei-led/cc-thingz/configuring-git-hygiene)<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/configuring-git-hygiene"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/configuring-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.
<a href="https://agentmods.dev/skills/alexei-led/cc-thingz/configuring-git-hygiene"><img src="https://agentmods.dev/badge/skills/alexei-led/cc-thingz/configuring-git-hygiene.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.00903 |
| Opus 5.5 | $0.00044 | $0.00361 |
| Sonnet 5.5 | $0.00022 | $0.00181 |
| Haiku 4.5 | $0.00011 | $0.00090 |
Grade A, and why
configuring-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 1mo 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Git Hygiene
Set up project-local hygiene that stays fast enough to keep enabled. Stop if the directory is not a git repo.
Ask first
Propose the plan (current facts, files and config to change, verification, risks) and get approval before you:
- write, replace, or merge into a hook file;
- set a
git configvalue (local or global) or runchmod; - run
git rm --cached; - install a tool, or choose whether a hook fails or skips when a tool is missing.
If the repo is dirty, show git status --short and ask before hook or config edits.
When asked for a plan, give the whole plan in one answer. If you have not inspected the repo yet, make the inspection commands below its first step, mark current state as unverified, and still lay out the hook, Gitleaks, or .gitignore changes from the policy and how you will verify them.
Inspect
git status --short
git config --show-origin --get core.hooksPath || true
git config --show-origin --list | rg '^(file:.*\s+)?(user\.|commit\.|tag\.|pull\.|fetch\.|rerere\.|core\.hooksPath|includeIf\.)' || true
git ls-files .gitignore .pre-commit-config.yaml .gitleaks.toml 2>/dev/null || true
ls -la .git/hooks .githooks scripts/git-hooks 2>/dev/null || true
Policy
- Extend the existing hook framework. Without one, use
pre-commit, then a project-localcore.hooksPathdirectory (git config --local core.hooksPath scripts/git-hooks). - Pre-commit runs only on staged or affected files: format, lint, touched-config validation, staged Gitleaks scan. No full tests, full builds, installs, or network calls.
- Pre-push runs the full build, test, type, and lint validation, plus a broader secret scan when practical.
- Run Gitleaks with
--redact, and keep secret values out of chat and external tools. - Hooks never auto-commit or restage files unless the repo already does.
- A hook that blocks legitimate work gets tuned;
--no-verifyis not the fix. .gitignorepatterns come from real artifacts and stay narrow.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed · -39 lines 64136a71eb65
- 2mo ago First seen · 114 lines · 111 tokens per session scan A 121c912e4711
configuring-git-hygiene is a skill published in the GitHub repository alexei-led/cc-thingz (38 stars, last pushed 4d ago), licensed MIT. It adds 111 tokens to every session and 903 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
autofix-pr
Watch a pull request and fix it from a worktree of its own - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once] [--every ] [--no-reply] [--yes] [instructions]…
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
ring:generating-pr-descriptions
Generating pull request descriptions from git branch changes with automatic title generation, change-type detection, and smart analysis. Uses branch-only scope to avoid full history analysis. Use when preparing a PR for review. Skip when the PR is a single trivial commit or description already exists.
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.