GitEasy: Skill for Claude Code

.claude/skills/release-qa-passes/SKILL.md

release-qa-passes is a skill for Claude Code from greenmtnsun/GitEasy. It costs 210 tokens per session (1,369 once invoked), scanned A, original, MPL-2.0.

A release-time quality review process for checking a test suite, preparing regression checks, and attacking a new feature from several angles. It runs at milestones or releases, not on every code change.

In plain words
What is it for?
Use it to audit tests at a milestone, build a regression pack before releasing, and identify work items for testing a new feature.
Why use it?
It helps find missing or weak tests before a release without turning these judgment-based reviews into noisy per-commit checks.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: names the AskUserQuestion tool.

This is greenmtnsun/GitEasy's own configuration. It tells Claude Code how to work on GitEasy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything GitEasy configures →

Reuse

Borrowing it

Nothing to install: this file belongs to greenmtnsun/GitEasy. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/greenmtnsun/GitEasy/main/.claude/skills/release-qa-passes/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/greenmtnsun/GitEasy

Made for: Claude Code.

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 release-qa-passes

README.md
[![agentmods](https://agentmods.dev/badge/skills/greenmtnsun/giteasy/release-qa-passes/github.svg)](https://agentmods.dev/skills/greenmtnsun/giteasy/release-qa-passes)
Your own site
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/release-qa-passes"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/release-qa-passes/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 release-qa-passes

Your own site · 80×15
<a href="https://agentmods.dev/skills/greenmtnsun/giteasy/release-qa-passes"><img src="https://agentmods.dev/badge/skills/greenmtnsun/giteasy/release-qa-passes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 210 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,369 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 $0.00210 $0.01369
Opus 5.5 $0.00084 $0.00548
Sonnet 5.5 $0.00042 $0.00274
Haiku 4.5 $0.00021 $0.00137

Measured today against content hash 0877ca52ed38, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

release-qa-passes 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 today.

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.

.claude/skills/release-qa-passes/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

See also: delivery-pipeline (these passes are Verify-phase steps and log to its docs/PIPELINE.md ledger), honest-completion + verify-claims-on-disk (the claim discipline the rules below apply to QA findings).

Release QA passes

Origin and authority: Keith pointed Meta-Claude at a QA prompt library (Zero Defect Academy playlist), four of fourteen prompts survived trial on real suite material, and Keith approved adoption 2026-08-07. Full trial evidence and directive chain: C:\Users\keith\.claude\plans\Meta-to-dotclaude-qa-prompt-ci-integration-2026-08-07.md. Do not re-derive what that report already settled.

These are release-path passes, not per-commit gates. They are judgment passes that produce work items — there is no green/red answer, so running them per-commit adds cost and noise. SUITE-PR-GATE.md (canonical home: C:\Users\keith\.claude\cross-project-artifacts\SUITE-PR-GATE.md, fixed 2026-08-15) is the per-PR mechanical gate and is deliberately NOT where these live.

Standing discipline — applies to every pass, every run

Proven necessary in trial (a casual single-file run false-alarmed; the disciplined run produced six real findings and zero fabricated ones):

  1. Whole-repo context. Load the full source and every test suite before claiming a gap. Never run a pass on one pasted file.
  2. Verify on disk before reporting. Every claimed gap/duplicate/weak assertion gets checked against the actual files (e.g., search every test file before calling a behavior untested).
  3. Findings cite file:line in both source and tests.

Pass A — Test-suite audit (per milestone, or pre-release)

Audit the test coverage for [FUNCTION/FEATURE] across the whole repo (all test files, not one). Find: 1) coverage gaps — behavior in the source with no exercising test anywhere; 2) duplicate or near-duplicate tests; 3) weak assertions — tests that would still pass if the behavior regressed; 4) obsolete tests. For each finding: file:line in source and tests, why it matters, and the specific test to add/merge/strengthen. Verify each gap claim by searching every test file before reporting it.

Read the full file on GitHub · 75 lines

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. today First seen · 75 lines · 210 tokens per session scan A 0877ca52ed38

Subscribe to this mod's changes

release-qa-passes is a skill published in the GitHub repository greenmtnsun/GitEasy (1 stars, last pushed yesterday), licensed MPL-2.0. It adds 210 tokens to every session and 1,369 once invoked, about $0.0008 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 2026-11-18.

Related

release-qa-passes compared with skills from other repositories

release-qa-passes next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
release-qa-passesgreenmtnsun/GitEasySkill1yesterdayMPL-2.0A210Claude Code
imagegenopenai/codexSkill136ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill80kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill101ktodayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill395ktodayMITA36Claude Code
free-llm-apismnfst/awesome-free-llm-apisSkill14ktodayCC0-1.0A113Claude Code, Codex
next-cache-components-adoptionvercel/next.jsSkill144ktodayMITA95Claude Code