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.
npx agentmods add rules/prest/prest-mcp-adapter/git-commitsgit clone --depth 1 https://github.com/prest/prest-mcp-adapterWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00635 | $0.00635 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Commit Practices (prest-mcp-adapter)
Commits are a human action. The AI must never run git commit, git add (to stage for a commit), or git commit --amend — even when the user says "commit this" or "commit your changes."
When commits are in scope, the AI may inspect the repo and prepare a commit for the human; the human runs the final git commands locally.
What the AI Must Never Do
- Run
git commitorgit commit --amend - Run
git addto stage files for a commit - Create commits to "save progress" or after finishing a task
- Create empty commits
- Push to the remote unless the user explicitly asks (see Push below)
If the user asks you to commit, decline the git command and instead offer a ready-to-run suggestion (message + git add / git commit commands they can copy).
What the AI May Do
- Run read-only inspection:
git status,git diff,git log - Draft a commit message and list which paths to stage
- Warn about secrets (
.env, credentials, tokens, keys) that must not be committed - Fix hook/lint issues in code when asked — the human commits after validation
Git Safety Protocol
When any git write command is in scope (e.g. push, branch ops), still follow:
- Never update git config (
git config, global or local) - Never run destructive or irreversible commands (
push --force,reset --hard, etc.) unless the user explicitly requests them - Never skip hooks (
--no-verify,--no-gpg-sign, etc.) unless the user explicitly requests it - Never force-push to
mainormaster; warn the user if they ask - Never use interactive git (
git add -i,git rebase -i)
Suggesting a Commit (human runs these)
1. Inspect (run in parallel)
git status
git diff
git log -10 --oneline
2. Draft the message
- 1–2 sentences focused on why, not a file list
- Prefer Conventional Commits (
feat:,fix:,chore:,refactor:) - List only the paths the human should stage; never include secrets
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.
- 2d ago First seen · 71 lines · 635 tokens per session scan A 382da0005241
git-commits is a cursor rule published in the GitHub repository prest/prest-mcp-adapter (0 stars, last pushed 1mo ago), licensed MIT. It adds 635 tokens to every session, about $0.0032 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.
Other cursor rules, from other repositories
git-conventional-commit-messages
Cursor rules for Git development with conventional commit messages integration.
conventional-commits
This rule defines the format for creating commit messages.
git
辅助生成 git 提交信息.
incremental-verify
Verify each behavior before building the next. One test, one implementation, one commit. No bulk-writing tests for behavior that does not yet exist.
atomic-commits
Git best practices - atomic commits, descriptive messages, feature branches.
commitlint
Commitlint rules for conventional commit messages.