Git guardrails for Claude Code

Installs a Claude Code PreToolUse hook that stops the usual forms of git push, reset --hard, clean -f, branch -D and checkout or restore of the whole tree, for one project or all, then tests it. Use when you want a safety net against an agent pushing or discarding work on its own.

Git & PRsPack: Matt Pocock's skills95 linesgit-guardrails-claude-code
Author
Source
mattpocock/skills/skills/misc/git-guardrails-claude-code @ abeeaf9
License
MIT · Copyright (c) 2026 Matt Pocock

About this skill

What it does

The skill installs a safety net in Claude Code: a PreToolUse hook that searches the text of every Bash command for patterns from a list before it runs and stops the command on a match. The default list has git push (--force included), git reset --hard, git clean -f and -fd, git branch -D, git checkout . and git restore .. The agent gets exit code 2 and a message saying the user has prevented this.

In five steps the agent asks whether to protect this project (.claude/settings.json) or all projects (~/.claude/settings.json), copies the script, merges the hook into hooks.PreToolUse without touching other settings, asks which patterns to add or remove, and tests the script with a fake git push.

The folder ships scripts/block-dangerous-git.sh, the hook itself: it pulls the command out of the tool call with jq and looks for the patterns as substrings. It does not parse the command, so the same operation written another way gets through: git clean -df, git clean -xfd, git -C . push origin main, git checkout -- ., git branch --delete --force x. Without jq the script cannot read the command and silently lets everything through. agents/openai.yaml holds the name and short description for Codex.

When to use it, and when not

Use it when Claude Code runs unattended and you want a guard against the usual destructive git commands that holds better than a line in the instructions. It is a safety net, not a guarantee: a command written differently slips past it. The default list leaves history rewrites alone: git rebase and git commit --amend run unless you add them in step four.

Change the defaults if the agent should push its own branches: the git push pattern stops a plain push too. The hook goes into Claude Code's settings. Codex does not read them, so there is no block there; Cursor can pick up Claude Code hooks through its import of third-party settings, but check that the block actually fires there. The script needs bash and jq. Patterns match anywhere in the command line, so git checkout .env is blocked too, and so is a commit whose message mentions "git push".

How to run it

The install command below puts the whole folder in place. The agent picks the skill up by its description when you ask to block dangerous git commands; to call it yourself:

  • Claude Code: /git-guardrails-claude-code, or ask for the skill by name.
  • Codex: $git-guardrails-claude-code.
  • Cursor: type / in the Agent chat and pick git-guardrails-claude-code.

Example: /git-guardrails-claude-code Install it for all my projects and block git rebase as well.

How it differs from similar skills

Safe git recovery works the other end: it recovers work through the reflog after a reset or a lost branch. This skill tries to prevent the loss by stopping the usual dangerous commands before they run, but a command in an unusual form gets through, and then recovery is what helps. Git workflow and versioning suggests git reset --hard HEAD to return to the last good state; the default list blocks it, so pick one approach. Pre-commit hooks setup installs git hooks that check commits; this hook checks the agent's commands. Guardrails for destructive Docker commands covers the same risk for Docker, but as rules for the agent rather than a hook: it states what a command would delete and waits for your confirmation.

Install

Run one command — it saves SKILL.md and the files it uses into your agent's skills folder. Claude Code and Codex pick up a new skill without a restart; if it does not show up, restart the agent.

Claude Code — macOS, Linux
curl -fsSL --create-dirs -o ~/.claude/skills/git-guardrails-claude-code/SKILL.md https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/SKILL.md -o ~/.claude/skills/git-guardrails-claude-code/LICENSE https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/LICENSE -o ~/.claude/skills/git-guardrails-claude-code/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/agents/openai.yaml -o ~/.claude/skills/git-guardrails-claude-code/scripts/block-dangerous-git.sh https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/scripts/block-dangerous-git.sh && chmod +x ~/.claude/skills/git-guardrails-claude-code/scripts/block-dangerous-git.sh
Codex, Cursor — macOS, Linux
curl -fsSL --create-dirs -o ~/.agents/skills/git-guardrails-claude-code/SKILL.md https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/SKILL.md -o ~/.agents/skills/git-guardrails-claude-code/LICENSE https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/LICENSE -o ~/.agents/skills/git-guardrails-claude-code/agents/openai.yaml https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/agents/openai.yaml -o ~/.agents/skills/git-guardrails-claude-code/scripts/block-dangerous-git.sh https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/scripts/block-dangerous-git.sh && chmod +x ~/.agents/skills/git-guardrails-claude-code/scripts/block-dangerous-git.sh
Claude Code — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml','scripts/block-dangerous-git.sh') { $p = Join-Path "$HOME\.claude\skills\git-guardrails-claude-code" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/$f" -UseBasicParsing -OutFile $p }
Codex, Cursor — Windows PowerShell
foreach ($f in 'SKILL.md','LICENSE','agents/openai.yaml','scripts/block-dangerous-git.sh') { $p = Join-Path "$HOME\.agents\skills\git-guardrails-claude-code" $f; New-Item -ItemType Directory -Force (Split-Path $p) | Out-Null; Invoke-WebRequest "https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/$f" -UseBasicParsing -OutFile $p }

Any other agent: save the file into its skills folder, or give it the link to the file: https://anymodel.org/en/skills/matt-pocock/git-guardrails-claude-code/SKILL.md

SKILL.md

Raw

Setup Git Guardrails

Sets up a PreToolUse hook that intercepts and blocks dangerous git commands before Claude executes them.

What Gets Blocked

  • git push (all variants including --force)
  • git reset --hard
  • git clean -f / git clean -fd
  • git branch -D
  • git checkout . / git restore .

When blocked, Claude sees a message telling it that it does not have authority to access these commands.

Steps

1. Ask scope

Ask the user: install for this project only (.claude/settings.json) or all projects (~/.claude/settings.json)?

2. Copy the hook script

The bundled script is at: scripts/block-dangerous-git.sh

Copy it to the target location based on scope:

  • Project: .claude/hooks/block-dangerous-git.sh
  • Global: ~/.claude/hooks/block-dangerous-git.sh

Make it executable with chmod +x.

3. Add hook to settings

Add to the appropriate settings file:

Project (.claude/settings.json):

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/block-dangerous-git.sh"
          }
        ]
      }
    ]
  }
}

Global (~/.claude/settings.json):

{
  "hooks": {
    "PreToolUse": [
      {
        "matcher": "Bash",
        "hooks": [
          {
            "type": "command",
            "command": "~/.claude/hooks/block-dangerous-git.sh"
          }
        ]
      }
    ]
  }
}

If the settings file already exists, merge the hook into the existing hooks.PreToolUse array. Don't overwrite other settings.

4. Ask about customization

Ask if user wants to add or remove any patterns from the blocked list. Edit the copied script accordingly.

5. Verify

Run a quick test:

echo '{"tool_input":{"command":"git push origin main"}}' | <path-to-script>

Should exit with code 2 and print a BLOCKED message to stderr.

Connect through AnyModel API

This skill runs on whatever model your agent uses. Point Claude Code, Codex or Cursor at AnyModel to run it on Claude, GPT, Gemini and more with one key — pay per token, no subscription.

More from the pack Matt Pocock's skills

Code review against standards and spec

Reviews the diff since a commit, branch or tag on two axes in parallel subagents: the repo's written standards plus a baseline of Fowler code smells, and the originating spec or issue. Use when a branch or PR needs checking against its spec.

Deep module design

Fixes a shared vocabulary for deep modules (interface, seam, adapter, depth, leverage), with the deletion test, dependency categories and a design-it-twice pattern on parallel subagents. Use when designing a module's interface or deciding where a seam goes.

Diagnosing hard bugs

Diagnoses hard bugs and slowdowns by first building a fast, deterministic command that reproduces the exact symptom, then minimising it, ranking falsifiable hypotheses and adding a regression test at a real seam. Use when something fails, throws or got slow.

Domain modeling

Sharpens a project's domain language during design: challenges fuzzy or conflicting terms, writes resolved ones to GLOSSARY.md at once and offers a short ADR only for hard-to-reverse trade-offs. Use when discussing terminology or recording an ADR.

Implement a spec

Implements a spec and its tickets on one integration branch: a fresh implementer subagent per ticket in its own worktree, run in parallel along the blocking graph, then a code review and one fix pass. Use when the tickets from to-tickets are ready.

Improve codebase architecture

Finds shallow modules worth deepening, starting from the code that changes most, shows the candidates in an HTML report with before/after diagrams and grills the chosen one with you. Use when a codebase has grown hard to test or navigate.

Throwaway prototype

Builds throwaway code to answer one design question: a single-file clickable HTML demo for a state model, or several structurally different UI variants on one route switched by a URL param. Use when checking whether logic holds or how a page should look.

Coding session retrospective

Reviews a finished coding session from its logs and proposes changes to the agent's environment: navigation pointers, lint rules, pre-commit and CI checks, reviewer standards, tool use. Use when an agent session went slowly or made avoidable mistakes.

TDD with integration tests

Drives test-first work through public interfaces: agrees the seams to test with the user, runs one red-green cycle per test, mocks only at system boundaries and leaves refactoring to review. Use when building a feature or fixing a bug test-first.

Conversation to spec

Turns the current conversation and codebase into a spec with user stories, implementation and testing decisions, and publishes it to the issue tracker as ready-for-agent, without interviewing the user. Use when a discussed feature needs writing up.

Spec to tickets

Splits a spec, plan or conversation into tracer-bullet tickets, vertical slices that each fit one agent session, with blocking edges, and publishes them as local files or tracker issues. Use when work is too big for one session and needs a task graph.

Issue and PR triage

Triages issues and external PRs on the tracker: gives each a category and a state, checks for existing code and past rejections, reproduces bugs and writes agent briefs for ready work. Use when a maintainer works through incoming issues and PRs.

Wayfinder for huge work

Charts work too big for one agent session as a map issue with child decision tickets on the tracker, then resolves one ticket per session until the route to the goal is clear. Use when a large effort has open questions that block a spec or plan.

Bash wizard for manual steps

Generates an interactive bash script that walks a person through manual steps such as dashboard setup, API keys and CI secrets, opening each URL and saving values to .env and GitHub secrets. Use when setup or a migration needs steps only a human can take.

Migrate tests to shoehorn

Replaces as and as unknown as casts in TypeScript tests with fromPartial and fromAny from @total-typescript/shoehorn, adds the imports and runs the type check. Use when tests fake whole objects or cast partial test data to satisfy the compiler.

Pre-commit hooks setup

Sets up Husky and lint-staged in a Node repo so each commit runs Prettier on staged files, then the typecheck and test scripts, matched to the lockfile, and makes the first commit through the hook. Use when a repo has no commit-time checks.

Grilling a plan

Questions the user about a plan or decision in rounds of numbered questions with recommended answers, looks facts up itself through subagents and stops only when no decision is left assumed. Use when a plan needs stress-testing before work starts.

Teach me a topic

Runs a multi-session course in the current folder: a mission, trusted sources, short HTML lessons with quizzes, reference sheets and learning records that set the next lesson. Use when the user wants to learn a topic over time, not get one answer.

Decision questionnaire

Writes a Markdown questionnaire for someone who holds knowledge the user lacks, after asking only who it goes to and what answers are needed, with the most important questions first. Use when a decision depends on facts from another person.

Writing for agents

Gives the rules for writing text agents read: skill descriptions as context pointers, what to keep inline and what to move to a separate file, completion criteria, leading words and pruning. Use when creating or editing a skill, AGENTS.md or CLAUDE.md.