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 mir-am/skills-agents-ai-coding --skill git-pushgit clone --depth 1 https://github.com/mir-am/skills-agents-ai-codingWrote 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/mir-am/skills-agents-ai-coding/git-push)<a href="https://agentmods.dev/skills/mir-am/skills-agents-ai-coding/git-push"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/git-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/mir-am/skills-agents-ai-coding/git-push"><img src="https://agentmods.dev/badge/skills/mir-am/skills-agents-ai-coding/git-push.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 | $0.00017 | $0.02350 |
| Opus 5.5 | $0.00007 | $0.00940 |
| Sonnet 5.5 | $0.00003 | $0.00470 |
| Haiku 4.5 | $0.00002 | $0.00235 |
Grade A, and why
git-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 22d 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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
- Push new local commits on a feature branch to the remote
- Detect if an open PR exists for the current branch
- Update the PR's "Changes" section only when the push adds significant new functionality
- Update the existing PR-linked
CHANGELOG.mdentry only when the PR's high-level scope materially changes, using the PR URL in the changelog bullet, then commit that changelog change to the same branch before pushing - Skip PR updates for commits that fix bugs or mistakes from earlier commits in the same branch
- Preserve the existing PR Summary while appending new change entries
When to use me
Use this skill when the user asks to push commits and/or update the PR with the latest changes.
Prerequisites
- Must be on a feature branch (not master/main)
- Branch must have unpushed commits ahead of remote
- GitHub CLI (
gh) must be installed and authenticated - If
ghnot installed → error: "GitHub CLI not found. Install: https://cli.github.com/"
Validation Workflow
- Check current branch:
git branch --show-current - If on
masterormain→ error: "Error: Cannot push directly to master/main. Switch to a feature branch." - Check for unpushed commits:
git log origin/<branch>..HEAD --oneline - If no unpushed commits → inform user: "Nothing to push — branch is up-to-date with remote."
Push Workflow
- Check if branch exists on remote:
git ls-remote --heads origin <branch-name> - If the branch already exists on remote, treat the next push as the final push for this batch of local commits
- If the branch does not exist on remote yet, push it first:
git push -u origin <branch-name> - Only run pre-push PR detection, PR body updates, and changelog sync when the remote branch already exists and an open PR can already be associated with it
- If the branch was just published and a later changelog sync creates a dedicated
CHANGELOG.mdcommit, push a second time so that new changelog commit reaches the same branch - If the branch already existed on remote, finish with the normal push:
git push
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.
- 22d ago Changed · -1 lines 8d7aca695f80
- 1mo ago First seen · 199 lines · 17 tokens per session scan A 49ba255e37af
git-push is a skill published in the GitHub repository mir-am/skills-agents-ai-coding (2 stars, last pushed 23d ago), licensed MIT. It adds 17 tokens to every session and 2,350 once invoked, about $0.0001 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
github
GitHub CLI for issues, PRs, CI/check logs, comments, reviews, releases, repos, and gh api queries.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
release-publish
Publish an approved Orchard release.
release-review
Review Orchard deployment manifests.
orchard-release
Check deployment evidence and recovery conditions.
release-notes
Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.