commit

A set of Git rules for safely staging, committing, and pushing changes on the current branch.

In plain words
What is it for?
Checking the branch and worktree, staging only files changed in the current session, verifying the work, and requesting approval before pushing to `dev`.
Why use it?
It reduces the risk of committing unrelated work or changing protected branches such as `main` or `master`.

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/savedpixel/ai-agent-rules-generator/commit
Clone the repo
git clone --depth 1 https://github.com/savedpixel/ai-agent-rules-generator

Made for: Cursor.

Per session 1,067 This file is loaded in full into every session.
When invoked 1,067 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 $0.01067 $0.01067
Opus 5 $0.00534 $0.00534
Sonnet 5 $0.00213 $0.00213
Haiku 4.5 $0.00107 $0.00107

Measured yesterday against content hash 00892bbe0cc7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 yesterday.

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.

examples/glitch-payment-gateway/v1.1/cursor/generated/.cursor/rules/commit.mdc · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Commit Rules

Stage, commit, and push only the files you modified in this chat session to the current working branch. Do not include files changed by other tasks or tools.


Branch Safety (BLOCKING GATE)

  1. Check the current branch — run git branch --show-current.
  2. If on master or mainSTOP immediately. Do not stage, commit, or push. Tell the user and wait.
  3. If on dev — you may commit, but do NOT push automatically. After committing, ask: "Committed. Ready to push to dev?" Wait for explicit approval.
  4. Stay on the branch you started on. Never switch branches just to commit.
  5. Never push or commit directly to master or main unless explicitly instructed.

Verification Gate (BLOCKING)

Before committing, confirm that ALL required verification steps from the task plan have passed. If any verification is blocked or incomplete, do NOT commit. Report the blocker. See task.mdc → Blocker Protocol.


Steps

  1. Check git status --short — Review all modified and untracked files. Identify which ones you touched.

  2. Stage only your files — Use git add with explicit file paths. Never use git add -A or git add . because they can capture unrelated changes.

  3. Write a high-quality commit message using multiple -m flags. Never use one long quoted multi-line string.

    Commit Subject Rules

    <type>(<optional-scope>): <action-oriented summary>
    

    Allowed Types: feat, fix, refactor, docs, style, data, config, chore, merge

    Commit Subject Standards

    • Keep subjects under ~80 characters.
    • Use lowercase for type and scope.
    • Start with a clear verb (add, fix, move, remove, migrate, refine, etc.).
    • Be specific, not generic.
    • For multi-change sessions: summarize themes, put details in body.

    Commit Body Rules

    Use additional -m flags for body. Keep to 2–3 -m flags total.

    The body should:

    • Summarize key changes in one short paragraph (3–5 sentences max)
    • Mention most important modules or areas
    • Explain why if not obvious
    • Never enumerate every single change
    • End with Files: <key files touched>

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 1,067 tokens per session scan A 00892bbe0cc7

Subscribe to this mod's changes

commit is a cursor rule published in the GitHub repository savedpixel/ai-agent-rules-generator (7 stars, last pushed 4mo ago), licensed MIT. It adds 1,067 tokens to every session, about $0.0053 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 2026-08-31.