auto-commit

A rule that tells the coding agent to create a Git commit after each completed task that changes repository files.

In plain words
What is it for?
It applies conventional commit messages, commits only successful completed work, and pushes to a configured remote repository.
Why use it?
It keeps completed work recorded in small, focused commits and avoids leaving finished changes uncommitted.

Cursor rule for Cursor

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/quinnjr/google-mcp/auto-commit
Clone the repo
git clone --depth 1 https://github.com/quinnjr/google-mcp

Made for: Cursor.

Per session 275 This file is loaded in full into every session.
When invoked 275 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 $0.00275 $0.00275
Opus 5 $0.00138 $0.00138
Sonnet 5 $0.00055 $0.00055
Haiku 4.5 $0.00028 $0.00028

Measured 2d ago against content hash 3ea2c2198604, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

auto-commit 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 2d 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.

.cursor/rules/auto-commit.mdc · 43 lines

What it actually says

Auto-Commit After Agent Tasks

After completing any task that modifies files in the repository, the agent should commit the changes.

Rules

  1. Commit after every completed task - When a task is finished and files have been modified, stage and commit all changes before responding to the user.

  2. Use conventional commits - Follow the git-flow commit message format:

    <type>(<scope>): <subject>
    
  3. Push if remote is configured - After committing, push to the remote repository if one is set up.

  4. Atomic commits - Each task should result in a single, focused commit that represents the complete change.

  5. Don't commit partial work - Only commit when the task is fully complete and the code builds/lints successfully.

Workflow

After completing a task:

git add -A
git commit -m "<type>(<scope>): <descriptive message>"
git push  # if remote exists

Exceptions

Do NOT commit when:

  • The user explicitly asks not to commit
  • The task is exploratory (reading files, searching code)
  • The changes don't compile or have lint errors
  • The user is still iterating on the changes
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. 2d ago First seen · 43 lines · 275 tokens per session scan A 3ea2c2198604

Subscribe to this mod's changes

auto-commit is a cursor rule published in the GitHub repository quinnjr/google-mcp (11 stars, last pushed 4d ago), licensed MIT. It adds 275 tokens to every session, about $0.0014 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.