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 usrrname/cursorrules --skill git-commit-push-agentgit clone --depth 1 https://github.com/usrrname/cursorrulesWrote 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/usrrname/cursorrules/git-commit-push-agent)<a href="https://agentmods.dev/skills/usrrname/cursorrules/git-commit-push-agent"><img src="https://agentmods.dev/badge/skills/usrrname/cursorrules/git-commit-push-agent/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/usrrname/cursorrules/git-commit-push-agent"><img src="https://agentmods.dev/badge/skills/usrrname/cursorrules/git-commit-push-agent.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 | $0.00112 | $0.00477 |
| Opus 5.5 | $0.00045 | $0.00191 |
| Sonnet 5.5 | $0.00022 | $0.00095 |
| Haiku 4.5 | $0.00011 | $0.00048 |
Grade A, and why
git-commit-push 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 1mo 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.
What it actually says
Git Commit Standards
Critical Rules
- Use
git statusto check modified or staged files before committing - Never overwrite or push untracked files
- Commits MUST follow the conventional-commit standard
- Always run
git add <filename>from repo root - Use present tense in commit subject ("add" not "added")
- Subject ≤ 72 chars, imperative mood, blank line before body
- Reference issue/ticket with # if used
- Describe what or why, not how changes were made; fixes must state what was fixed
- Keep descriptions brief and focused—avoid verbose explanations
- Include agent name in commit footer ("Commit written by <agent_name>")
Commit Format
<type>(<scope>): <description> (#<issue-number>)
[optional body]
[optional footer]
Commit written by <agent_name>
- If agent not specified, use "cursor agent"
- Types: feat, fix, docs, style, refactor, perf, test, chore, ci, security, rename
Post-Commit Actions
- Do NOT include post-commit commands (e.g.,
npm run lint,git push) in commit message - Suggest these actions separately after commit
Agent Enforcement
- Always check
git statusbefore commit - Never use generic messages ("update code", "commit changes")
- Identify change type per conventional commit
- Commit body should be concise and brief, and should not exceed 20 words
- Prefer single-line descriptions when possible; only use body for essential context
- Use meaningful scope (codebase area)
- Clear, concise, imperative subject
- Add agent name as (co-)author
- Convert user commit instructions to proper format
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.
- 1mo ago First seen · 51 lines · 0 tokens per session scan A a45fbe13fa9c
git-commit-push is a skill published in the GitHub repository usrrname/cursorrules (11 stars, last pushed 6mo ago), licensed ISC. It adds 112 tokens to every session and 477 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
housekeep-dead-code
Remove dead code by category — one commit each, typecheck and tests between, bisect on red — then add a Knip ratchet. Use when "delete the dead code", "remove unused files", or "wire up Knip". Audit first → plan-dead-code. README/deps → workflow-housekeep.
git-notes
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
commit
Create well-formatted commits with conventional commit messages and emoji.
commit
Write clear commit messages in conventional commits format. Use when the user is done with changes and wants to commit, says 'commit this', asks for a commit message, or has staged changes ready to go.
git-hygiene-enforcer
Establishes git workflow guardrails including conventional commits, commit message hooks, branch naming conventions, PR templates, and code review processes. Provides hook configurations, workflow templates, and emergency bypass instructions. Use when users request "setup git hooks", "enforce commit conventions", "add…
secrets-scanner
Detects leaked API keys, tokens, passwords, and credentials in code with pre-commit hooks, CI checks, scanning rules, and remediation procedures. Use for "secret scanning", "credential detection", "API key leaks", or "secret management".