metagit-release-audit

metagit-release-audit is a skill for Claude Code, Codex from metagit-ai/metagit-cli. It costs 59 tokens per session (328 once invoked), scanned A, original, MIT.

A release-readiness check for repositories whose files have changed. It runs formatting, linting, tests, integration tests, and selected security checks before hand-off or release.

In plain words
What is it for?
Use it before handing over work, pushing changes, or releasing a project to run the repository’s pre-push quality gate and report any blockers.
Why use it?
It catches code-quality, test, and security problems before changes are pushed or declared complete. The checks vary according to which files changed.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it before handing over work, pushing changes, or releasing a project to run the repository’s pre-push quality gate and report any blockers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metagit-ai/metagit-cli/metagit-release-audit
Install

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.

Any agent
npx skills add metagit-ai/metagit-cli --skill metagit-release-audit
Clone the repo
git clone --depth 1 https://github.com/metagit-ai/metagit-cli

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for metagit-release-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-release-audit/github.svg)](https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-release-audit)
Your own site
<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-release-audit"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-release-audit/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.

agentmods 80×15 button for metagit-release-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/metagit-ai/metagit-cli/metagit-release-audit"><img src="https://agentmods.dev/badge/skills/metagit-ai/metagit-cli/metagit-release-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 328 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00059 $0.00328
Opus 5 $0.00030 $0.00164
Sonnet 5 $0.00012 $0.00066
Haiku 4.5 $0.00006 $0.00033

Measured 10d ago against content hash c668c2a9ede8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

metagit-release-audit 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 10d 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.

.agents/skills/metagit-release-audit/SKILL.md · 35 lines

What it actually says

Auditing Release Readiness

Use this skill whenever your session added or edited tracked files in this repository and you are about to hand off or say the task is done—not only “release” workflows. Read-only Q&A with no writes can skip it.

Workflow

  1. Run the pre-push quality gate.
  2. Capture failing stage logs and iterate fixes.
  3. Re-run until all required checks pass.
  4. Return a short readiness summary.

Commands

  • task qa:prepush
  • task qa:prepush:loop -- 3 (optional bounded retry loop)

Output Contract

Return:

  • pass/fail status by stage (including security_sync / security_audit / security_bandit when triggered)
  • unresolved blockers (if any)
  • push readiness recommendation

Security in the gate is context-aware: lockfile changes run uv sync --frozen --all-extras + pip-audit + bandit; src/ changes run pip-audit + bandit; docs-only diffs skip security. Use task security:scan for a full manual run.

Safety

  • Do not claim readiness unless checks are actually green.
Changes

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.

  1. 10d ago First seen · 35 lines · 59 tokens per session scan A c668c2a9ede8

Subscribe to this mod's changes

metagit-release-audit is a skill published in the GitHub repository metagit-ai/metagit-cli (3 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 328 once invoked, about $0.0003 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.