130-git

130-git is a cursor rule for coding agents from d-padmanabhan/agent-engineering-handbook. It costs 866 tokens per session, scanned A, original, MIT.

A set of mandatory rules for safe Git operations, where Git is the version-control system used to track code changes. It covers authorization, preserving existing work, commit signing, and remote changes.

In plain words
What is it for?
It is for inspecting repository state, protecting unrelated changes, approving commits, running required checks, and controlling operations that affect remote Git history.
Why use it?
It prevents accidental loss of files or history and requires checks before commits or changes to shared repositories.

Cursor rule

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add rules/d-padmanabhan/agent-engineering-handbook/130-git
Clone the repo
git clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbook

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for 130-git

README.md
[![agentmods](https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/130-git.svg)](https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/130-git)
Your own site
<a href="https://agentmods.dev/rules/d-padmanabhan/agent-engineering-handbook/130-git"><img src="https://agentmods.dev/badge/rules/d-padmanabhan/agent-engineering-handbook/130-git.svg" alt="Measured on agentmods" height="20"></a>
Per session 866 This file is loaded in full into every session.
When invoked 866 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00866 $0.00866
Opus 5 $0.00433 $0.00433
Sonnet 5 $0.00173 $0.00173
Haiku 4.5 $0.00087 $0.00087

Measured 3d ago against content hash 2fb7307136f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

130-git scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

rules/130-git.mdc · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Git Agent Gates

This rule contains only mandatory policy. Use the Git workflow skill (${HANDBOOK_ROOT}/skills/git-workflow/SKILL.md) for procedures, command sequences, examples, recovery, branch strategy, and commit formatting.

Preserve User Work

  • Inspect git status --short, the current branch, and HEAD before repository edits.
  • Preserve unrelated staged, unstaged, and untracked changes.
  • Never run a worktree-discard operation unless the user explicitly authorizes the exact command and affected paths:
    • git restore
    • git checkout -- <path>
    • git reset --hard
    • git clean -f
  • Do not stash user work merely to simplify the agent's workflow. Use a stash only when the operation genuinely requires a clean tree, explain its contents, and restore it promptly.
  • Do not delete branches, remove worktrees, or rewrite shared history without explicit authorization.

The broader checkpoint, verification, remote-mutation, and audit policy is canonical in 020-agent-audit.mdc (${HANDBOOK_ROOT}/rules/020-agent-audit.mdc).

Commit Authorization and Signing

Before executing git commit:

  1. Run applicable tests, lint, formatting, type checks, and build/package checks.

  2. Show the complete commit message:

    ==================== COMMIT MESSAGE PREVIEW ====================
    <type>(<scope>): <imperative summary>
    
    - <Key change>
    - <Key change>
    
    <Optional rationale>
    ================================================================
    
  3. Show the exact staged file list, including added, modified, renamed, and deleted files.

  4. Ask for explicit confirmation and wait for it.

Commit messages use Conventional Commits, an imperative summary of at most 72 characters, and concise rationale-focused bullets when useful. Detailed formats and examples live in the Git workflow reference (${HANDBOOK_ROOT}/skills/git-workflow/git-workflow.md).

Cryptographic commit signing is mandatory unless the repository documents an explicit exception:

Read the full file on GitHub · 78 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 78 lines · 866 tokens per session scan A 2fb7307136f1

Subscribe to this mod's changes

130-git is a cursor rule published in the GitHub repository d-padmanabhan/agent-engineering-handbook (16 stars, last pushed 4d ago), licensed MIT. It adds 866 tokens to every session, about $0.0043 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.