Git Safety logo

Git Safety

Community
waynesutton
git-safety

Stops an agent from destroying uncommitted work with git. Requires git status and git diff before any command that discards changes, treats "revert" and "undo" as manual edits, and never runs reset, checkout, clean, stash drop, or force push without explicit approval. Use when a task involves reverting, undoing, resetting, cleaning, rebasing, or force pushing, or before any git command in a repo with uncommitted changes.

Overview

Publisherwaynesutton
Repositorybuilder-skills
Skill namegit-safety
Stars
405
Forks
33
Bundled files
3
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by waynesutton on GitHub. Read the source before you install it.

Installation

Install the Git Safety AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/waynesutton/builder-skills/tree/main/skills/git-safety
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/waynesutton/builder-skills.git /tmp/builder-skills
mkdir -p .claude/skills
cp -r /tmp/builder-skills/skills/git-safety .claude/skills/git-safety
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Git Safety in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Git Safety on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Git Safety is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Git safety

These rules exist because one git checkout -- . erased two days of work. Follow them every time, not only when it feels risky.

Before any git command

  1. git status. Read it.
  2. If anything is modified or untracked, stop. Say what is there. Ask before proceeding with anything that could touch those files.
  3. Suggest git stash push -m "<why>" if the user needs a clean tree and wants the work kept.

Commands that need explicit approval

Never run these on your own. Show the exact command, say what it will destroy, and wait for a yes.

CommandWhat it destroys
git reset --hardevery uncommitted change
git checkout -- <file> or git restore <file>uncommitted changes in that file
git checkout -- . or git restore .uncommitted changes in every file
git clean -fdevery untracked file and folder
git stash drop or git stash clearstashed work
git push --force or --force-with-leaseremote history other people may have
git branch -Da branch and any commits only it holds
git rebase on a shared branchcommit ids other people have

"Explicit approval" means the user saw the command and said yes to it. A general "go ahead" from earlier in the conversation does not count.

Revert and undo mean edit

When the user says "revert that", "undo that", or "go back":

  1. Ask which change. Committed or uncommitted? All of it or one part?
  2. git diff <file> to see exactly what would be lost.
  3. Read the current file.
  4. Edit the file by hand to remove the specific lines that are wrong. Keep everything else.
  5. Show the result.

Do not reach for git checkout or git restore. They remove everything in the file, including the parts the user liked.

For committed changes, git revert <sha> is safe because it creates a new commit. Still show the sha and the commit message first.

Diff before discard

Any time a change is about to be thrown away, the user sees git diff output for it first. No exceptions. If the diff is long, show git diff --stat and offer the full diff.

Commits, pushes, deploys

Do not commit, push, tag, publish, or deploy unless the user asks in the current message. When the work is done, print a suggested commit message and stop.

Suggested commit:
fix: dedupe heartbeat writes within 10s window

Safe defaults

These are fine to run without asking:

  • git status, git log, git diff, git show, git blame
  • git stash push -m "<message>" when the user asked for a clean tree
  • git add <specific files> when the user asked to commit
  • git checkout -b <new-branch> from a clean tree
  • git revert <sha> after showing the commit

Checklist

Before a git command:

  • git status ran and I read it
  • no uncommitted work is in the blast radius, or the user approved
  • I showed git diff for anything being discarded
  • the command is not in the approval table, or the user said yes to this exact command

When asked to revert or undo:

  • I know which change and whether it is committed
  • I am editing the file, not checking it out
  • everything the user did not mention stays

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Git Safety AI skill do?

Stops an agent from destroying uncommitted work with git. Requires git status and git diff before any command that discards changes, treats "revert" and "undo" as manual edits, and never runs reset, checkout, clean, stash drop, or force push without explicit approval. Use when a task involves reverting, undoing, resetting, cleaning, rebasing, or force pushing, or before any git command in a repo with uncommitted changes.

Why use Git Safety on TypingMind?

Because you install it once and use it with any model. Git Safety is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Git Safety in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/waynesutton/builder-skills/tree/main/skills/git-safety. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Git Safety?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Git Safety?

As many as you like. As long as a model supports skills, you can use Git Safety with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Git Safety AI skill free?

Yes. It is published on GitHub by waynesutton under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇