run-qa-gate

run-qa-gate is a skill for Claude Code, Codex from Espenandreass1/agentslice. It costs 25 tokens per session (302 once invoked), scanned A, original, MIT.

A release-checking workflow that independently tests a completed software change against its approved requirements. It returns a pass, pass with notes, or fail decision.

In plain words
What is it for?
Use it after implementation to run relevant acceptance tests, regression checks, linting, type checks, builds, or database checks before release.
Why use it?
It reduces the risk of releasing code that does not meet the agreed requirements or has an overlooked regression. It also records checks that could not run and their remaining risk.

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 after implementation to run relevant acceptance tests, regression checks, linting, type checks, builds, or database checks before release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/espenandreass1/agentslice/run-qa-gate
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 Espenandreass1/agentslice --skill run-qa-gate
Clone the repo
git clone --depth 1 https://github.com/Espenandreass1/agentslice

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 run-qa-gate

README.md
[![agentmods](https://agentmods.dev/badge/skills/espenandreass1/agentslice/run-qa-gate.svg)](https://agentmods.dev/skills/espenandreass1/agentslice/run-qa-gate)
Your own site
<a href="https://agentmods.dev/skills/espenandreass1/agentslice/run-qa-gate"><img src="https://agentmods.dev/badge/skills/espenandreass1/agentslice/run-qa-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 302 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 $0.00025 $0.00302
Opus 5 $0.00013 $0.00151
Sonnet 5 $0.00005 $0.00060
Haiku 4.5 $0.00003 $0.00030

Measured yesterday against content hash 8d74df673be8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

run-qa-gate 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 yesterday.

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.

kit/.agents/skills/run-qa-gate/SKILL.md · 34 lines

What it actually says

Run QA Gate

Read

Verify the workspace and minimal preflight. Read the PR, changed files, QA plan, and at most one directly relevant prior report. Add a controlled spec only if it exists.

Guardrails

  • Use a separate QA agent when available; otherwise switch to a critical independent role.
  • Confirm PR lane and policy-sensitive paths before selecting checks.
  • FAIL blocks merge/release/deployment.

Check selection

  • Default: focused acceptance tests, relevant domain regression, lint, and typecheck for code.
  • Broaden only for shared contracts, auth/ownership, database/RLS/migrations, public/commerce flows, build/framework/deploy configuration, or production release.
  • Docs needs affected-guidance review, not an application test, build, or Vercel preview.

Steps

  1. Verify outcome, scope, lane, and risk against the PR and policy.
  2. Run selected checks and state why they fit; list deferred checks and residual risk.
  3. Record independent PASS, PASS WITH NOTES, or FAIL in the PR.
  4. Create a separate QA report only when risk/auditability needs it, and link it from the PR.

Output

Give result, compact checks, residual risk, and merge/release decision needed. Do not repeat the PR plan.

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. yesterday Changed 8d74df673be8
  2. 8d ago First seen · 34 lines · 25 tokens per session scan A d5895cfa0175

Subscribe to this mod's changes

run-qa-gate is a skill published in the GitHub repository Espenandreass1/agentslice (4 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 302 once invoked, about $0.0001 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.