When the agent reaches for it
The agent keeps every installed skill's description in view and loads the full instructions when a request matches. This is the description it reads:
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
What the instructions cover
The sections of its SKILL.md, in order.
- What Gets Blocked
- Steps
What ships with it
Besides SKILL.md, the folder carries these. The agent opens them only when a step in the instructions calls for one.
-
agents/ -
scripts/
Install the Git guardrails for Claude Code skill
For Claude Code, run this in a terminal. It comes from the publisher's own instructions.
npx skills@latest add mattpocock/skills License: MIT.
In Longwave, add Engineering Skills from the marketplace. It installs all 37 of its skills, and your Claude Code, Codex and OpenCode threads can use them.