git-commits

A set of rules for safe Git commits. It says to create a commit only when the user explicitly asks and lists files, settings, and destructive actions to avoid.

In plain words
What is it for?
Checking whether a commit is allowed, preparing a safe commit, and following safeguards around configuration, hooks, protected branches, and sensitive files.
Why use it?
It prevents unrequested commits, unsafe Git operations, and accidental inclusion of secrets or generated project data.

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/openjkai/secscan_mcp/git-commits
Clone the repo
git clone --depth 1 https://github.com/openjkai/secscan_mcp

Made for: Cursor.

Per session 292 This file is loaded in full into every session.
When invoked 292 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 $0.00292 $0.00292
Opus 5 $0.00146 $0.00146
Sonnet 5 $0.00058 $0.00058
Haiku 4.5 $0.00029 $0.00029

Measured yesterday against content hash 39a83a9e75c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

git-commits 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.

.cursor/rules/git-commits.mdc · 38 lines

What it actually says

Git commits

When to commit

  • Only create a git commit when the user explicitly asks
  • If unclear, ask first — do not commit proactively

Safety

  • NEVER update git config
  • NEVER run destructive git commands (push --force, hard reset, etc.) unless explicitly requested
  • NEVER skip hooks (--no-verify) unless explicitly requested
  • NEVER force-push to main/master — warn the user if they request it
  • Avoid git commit --amend unless all apply: user requested amend, HEAD commit is yours this session, not pushed
  • Do not commit: .env, *.pem, *.key, credentials.json, .scan-output/, real secrets in fixtures

Commit workflow (when user asks)

  1. Parallel: git status, git diff, git log (recent messages for style)
  2. Draft a 1–2 sentence message focused on why
  3. Stage relevant files, commit with HEREDOC message, verify with git status
  4. Do not push unless the user asks

Message format

Short imperative summary (50 chars or less if possible)

Optional body: why this change matters.

Example: Add gitleaks adapter with normalized secret findings

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 · 38 lines · 292 tokens per session scan A 39a83a9e75c3

Subscribe to this mod's changes

git-commits is a cursor rule published in the GitHub repository openjkai/secscan_mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 292 tokens to every session, about $0.0015 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.