setup-git-guardrail
Skill0 starsChanged 3 months agoNo licenceView on GitHub
Install git hooks that keep the primary clone parked on `main` and push all work into worktrees — refusing commits made in the primary, catching the paths `pre-commit` never sees (`cherry-pick`, `revert`, `reset --hard`, `--no-verify`), and warning when the primary drifts off `main` — plus a Claude Code `SessionStart` hook that restates that drift in later sessions. Use when the user says "set up git guardrails", "install guardrails", "protect main", "prevent commits to main", "stop me committing in the primary clone", "add the git hooks", "set up branch protection", "update the git hooks", "the primary is on the wrong branch", "detect drift off main". Checks what git already enforces first, verifies by testing the failure path, and states plainly where the guardrail can be bypassed.
- Deletes or force-pushes
In this repository18 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- user-prompt/CLAUDE.mdCLAUDE.md
- afkSkill
- aws-sso-sessionsSkill
- delegateSkill
- dev-toolsSkill
- duckSkill
- handoffSkill
- housekeepingSkill
- house-styleSkill
- low-fuelSkill
- machine-health-scheduleSkill
- machine-healthSkill
- mergeSkill
- sync-configSkill
- tddishSkill
- tldrSkill
- wrap-upSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.