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 Kevin-Liu-01/Agent-Machines --skill commit-and-pushgit clone --depth 1 https://github.com/Kevin-Liu-01/Agent-MachinesWrote 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/kevin-liu-01/agent-machines/commit-and-push)<a href="https://agentmods.dev/skills/kevin-liu-01/agent-machines/commit-and-push"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/commit-and-push/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/kevin-liu-01/agent-machines/commit-and-push"><img src="https://agentmods.dev/badge/skills/kevin-liu-01/agent-machines/commit-and-push.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.00808 |
| Opus 5.5 | $0.00028 | $0.00323 |
| Sonnet 5.5 | $0.00014 | $0.00162 |
| Haiku 4.5 | $0.00007 | $0.00081 |
Grade A, and why
commit-and-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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit and Push
Handle the common "just get this committed and pushed" workflow without drifting into PR creation.
When to use
Use this skill when the user explicitly wants git changes committed and pushed, but does not ask for a pull request.
Examples:
- "commit and push"
- "commit these to a new branch called
kevin/updated-dashboard" - "stage this and push it"
- "push the current work with an explanation of the changes"
If the user wants a PR too, use yeet instead.
Workflow
1. Inspect before staging
Always gather context first:
git status --short
git diff --stat
git diff --cached --stat
git log --oneline -6
You are looking for:
- unrelated dirty files
- generated artifacts
- screenshots, traces, or browser logs
- obvious secrets (
.env, credentials, tokens) - the repo's recent commit style
2. Decide branch behavior
- If the user provided a branch name, use it.
- If the current branch is already a feature branch, stay on it unless the user asked otherwise.
- If the current branch is
main/masterand the user did not explicitly ask to push there, create a feature branch first, preferablykevin/<slug>.
Use non-destructive branch commands only:
git switch -c <branch>
git switch <branch>
Never use git checkout or git restore as the default path.
3. Stage intentionally
Do not blindly add everything if the tree includes junk. Exclude generated browser artifacts, scratch outputs, and anything that should not ship.
Typical exclusions:
.playwright-mcp/- screenshots or trace dumps created only for verification
- local env files
- transient build output unless the repo intentionally tracks it
If the user said "everything," interpret that as everything relevant to the requested work, not every piece of machine exhaust in the working tree.
4. Validate once if warranted
If the changes are code and the repo has an obvious targeted validation command, run it once before committing. Prefer the narrowest meaningful check.
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 · 126 lines · 71 tokens per session scan A 7f86df2d06ce
commit-and-push is a skill published in the GitHub repository Kevin-Liu-01/Agent-Machines (30 stars, last pushed 3d ago), licensed MIT. It adds 71 tokens to every session and 808 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 2026-08-30.
Other skills, from other repositories
diff-review
Render the patch-edit run's accumulated changes as a reviewable diff, surface it through a GenUI choice surface, and persist the user's accept / reject decision into the artifact manifest.
git-wrapup
Land working-tree changes as logical commits — the work grouped by concern, topped by a release commit (version bump, changelog, regenerated artifacts). The work commits land first, then the version bump, verification, and the release commit on top. Stops at "committed locally on main" — or, when the project releases…
github-commenting
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.
coding-worktree-recovery
Use this skill when coding-agent work is interrupted, an agent exits without a clean commit, multiple controllers target the same checkout, or the checkout produces inconsistent file/Git behavior.
studio-source-control
Drive a scoped application's linked git repository from the instance — what has to be true before Source Control works at all, the commit-then-push order, stashes and branches over /api/snsourcecontrol, and when this replaces update sets rather than sitting next to them.
french-commit-message
Rédige un message Conventional Commits en français à partir d'un diff fourni ou des changements Git indexés. À utiliser pour une demande de message de commit ou de résumé de diff en français.