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 skills add Phaedra-Solutions/cursor-rules --skill git-commitgit clone --depth 1 https://github.com/Phaedra-Solutions/cursor-rulesWrote 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.
[](https://agentmods.dev/skills/phaedra-solutions/cursor-rules/git-commit)<a href="https://agentmods.dev/skills/phaedra-solutions/cursor-rules/git-commit"><img src="https://agentmods.dev/badge/skills/phaedra-solutions/cursor-rules/git-commit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/phaedra-solutions/cursor-rules/git-commit"><img src="https://agentmods.dev/badge/skills/phaedra-solutions/cursor-rules/git-commit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00065 | $0.00978 |
| Opus 5.5 | $0.00026 | $0.00391 |
| Sonnet 5.5 | $0.00013 | $0.00196 |
| Haiku 4.5 | $0.00006 | $0.00098 |
Grade A, and why
git-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 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git commit
When to use
- The user asks you to commit, write a commit message, or "save this to git".
Never commit on your own initiative, even at the end of a task.
Before you start
- Check the repo state with
git status --shortand the current branch withgit branch --show-current. - If changes are already staged, the commit covers only those. If nothing is staged, ask which files to include; never stage unrelated changes or files you didn't touch without asking.
- Check for a project commit convention (Conventional Commits,
commitlint.config.*, aCONTRIBUTING.mdsection, a commit template). If one exists, follow it and keep the dash-list body below the required header. Otherwise use the format below.
Steps
-
Inspect the changes with git. Read the actual diff, not just file names:
git diff --staged --stat git diff --staged(Use
git difffor unstaged changes the user wants to include, after they confirm.) -
Make notes of what changed, grouped by intent rather than by file.
-
Draft the message as a dash list, one line per change:
- concise, in present tense ("Add", "Fix", "Remove", not "Added" or "Adds");
- focused on what changed, not how you did it;
- short lines; keep the whole message small. Split unrelated work into separate commits instead of one long message.
-
Show the message as plain text and ask for approval. Show only the message, not the command:
- Add rate limiting to the login endpoint - Fix the empty-state message on the orders page - Remove the unused date helperWait for the user to approve or edit it.
-
Scan staged files for secrets if gitleaks is installed (see
secrets-scan):gitleaks git --staged --redact --no-banner -vIf it finds anything, stop, tell the user what and where (never the value), and follow
secrets-scan. If gitleaks isn't installed, check the diff yourself for keys, tokens, passwords,.envfiles and private keys, and say that you did a manual check. -
Commit with the approved lines, one argument per line:
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.
- 3d ago First seen · 77 lines · 65 tokens per session scan A 87892d92233c
git-commit is a skill published in the GitHub repository Phaedra-Solutions/cursor-rules (4 stars, last pushed 2d ago), licensed MIT. It adds 65 tokens to every session and 978 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-11-01.
Other skills, from other repositories
git-github-flow
Use for branch prep, clean commits, PR descriptions, GitHub issue triage, changelogs, release notes, review response, merge readiness, or publishing a branch safely.
commit
Stage, commit, and push code changes with branch safety and explicit staging. Use when ready to commit work. Invoked by saying "commit", "push", or "commit and push".
commit-all
Batch-commit all uncommitted changes grouped by relevance. Use when multiple accumulated changes need committing. Invoked by saying "commit all" or "commit everything".
autofix-pr
Watch a pull request and fix it from a worktree of its own (or, with --in-place, the user's own checkout) - CI failures, review feedback from trusted authors and merge conflicts are fixed, pushed to the PR branch and answered on the PR under the user's git and gh identity. Usage - /autofix-pr [ | ] [--once]…
ax-extract-workflow
Reconstruct workflow behind a past coding-agent artifact using local ax sessions/commits/skills/tool traces. Use when asked how X was built.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.