Git Guardrails Claude Code

Set up Claude Code hooks to block dangerous git commands (push.

Copy setup link

Works in any agent

mattpocock/skillspinned c55ee46

✓ Security state: reviewed

2 static scans, 0 counted findings.

Recorded for this package revision; Edge checks the exact bundle again when your agent loads it.

SKILL.md3 files · 2.9 KB

From mattpocock’s public repository. Edge did not write or edit this skill.

What this skill does for you

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.

Quoted from the skill description in the pinned source

Use it with Edge

Set up Edge for me: read getedge.cc/SKILL.md and follow it. Then use Edge to load the git-guardrails-claude-code skill from mattpocock/skills.

Paste it into Claude, ChatGPT, Codex or Cursor.

Or read the skill source first.

Security evidence

Security state at 2026-10-15: reviewed. State definitions. This records static evidence for this revision; live load eligibility is checked again.

2 static scans, 0 counted findings. The listed scanners recorded the results shown for this package revision.

Scanner	Date	Result	Findings
Edge static checks	2026-09-29	Pass	0
Edge committed-secret checks	2026-09-29	Pass	0

Static scans check the code, not how well the skill works.

Scanner scope, raw findings and mirrored provider records

Edge static checks (Edge-run): edge-static/1.0.0. Scope: Static patterns for remote execution, credentials with network sends, obfuscation, prompt overrides, hidden Unicode, binaries and persistence. Revision: c55ee46073ed923f86ce59a5eb3b6d895095d1b7. Raw findings: not supplied. Counted findings: .

Edge committed-secret checks (Edge-run): edge-secrets/1.0.0. Scope: Credentials committed in the skill's files (values never shown). Revision: c55ee46073ed923f86ce59a5eb3b6d895095d1b7. Raw findings: not supplied. Counted findings: .

Socket (skills.sh mirror): Version unavailable. Scope: Not supplied by the mirrored record. Revision: not supplied. Raw findings: not supplied. Counted findings: Not supplied.

Snyk (skills.sh mirror): Version unavailable. Scope: Not supplied by the mirrored record. Revision: not supplied. Raw findings: not supplied. Counted findings: Not supplied.

Source and licence

Repository: https://github.com/mattpocock/skills
Pinned skill file: View source at revision
Revision: c55ee46073ed923f86ce59a5eb3b6d895095d1b7
Package hash: sha256:62a6811114183b09ccdd03e9f84ce7b50d9d30929d9f534d6f6ebf672f0cd7ad
Licence: MIT

Files in the scanned package

3 files, 2.9 KB at revision c55ee46073ed. Each link opens the file on GitHub at that pinned revision.

File	Size
SKILL.md	2.3 KB
agents/openai.yaml	112 bytes
scripts/block-dangerous-git.sh	507 bytes

Try Git Guardrails Claude Code in your agent.

Set up Claude Code hooks to block dangerous git commands (push.

Copy setup link