qa

qa is a skill for Claude Code, Codex from Everyone-Needs-A-Copilot/claude-copilot. It costs 44 tokens per session (887 once invoked), scanned A, original, MIT.

A software quality review process for reproducing bugs, checking fixes, designing tests, and verifying that a change meets its requirements. It also covers edge cases such as invalid input, permissions, timing conflicts, and recovery paths.

In plain words
What is it for?
Use it to investigate defects, plan regression checks, review tests, verify acceptance criteria, and assess product-facing changes such as accessibility or responsive behaviour.
Why use it?
It helps catch failures that a successful build may not reveal and records remaining risks honestly. It focuses on observed behaviour rather than assuming the implementation is correct.

Skill for Claude CodeCodex

Part of the claude-copilot plugin — 72 skills, 17 commands, 17 agents, 4 hooks shipped together

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.

agentmods
npx agentmods add skills/everyone-needs-a-copilot/claude-copilot/qa
Any agent
npx skills add Everyone-Needs-A-Copilot/claude-copilot --skill qa
Clone the repo
git clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilot

Made for: Claude Code, Codex.

Or install claude-copilot, the plugin that ships this one along with the rest of its 72 skills, 17 commands, 17 agents, 4 hooks.

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 qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/qa.svg)](https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/qa)
Your own site
<a href="https://agentmods.dev/skills/everyone-needs-a-copilot/claude-copilot/qa"><img src="https://agentmods.dev/badge/skills/everyone-needs-a-copilot/claude-copilot/qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 887 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00044 $0.00887
Opus 5 $0.00022 $0.00443
Sonnet 5 $0.00009 $0.00177
Haiku 4.5 $0.00004 $0.00089

Measured today against content hash 20d0789dbae7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

qa 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.

plugins/codex-copilot/skills/qa/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Engineer

Use this skill to make quality concrete.

Operating Lens

  • Verify behavior, not just builds.
  • Reproduce defects before fixing when possible.
  • Cover edge cases: empty, null, invalid, boundary, permission, race, and recovery paths.
  • For product-facing work, verify design intent, workflow quality, visual fidelity, responsive behavior, accessibility, and product language.
  • Check alignment with SOUL.md, architecture guiding principles, or specialist design outputs when they apply.
  • Prefer deterministic tests that explain the expected behavior.
  • Report residual risk honestly.
  • Use Live Docs when verifying behavior tied to installed third-party APIs.

Success Criteria

  • Acceptance criteria are explicit.
  • Relevant tests or checks are run and reported.
  • Edge cases and regression paths are covered in proportion to risk.
  • Product-facing changes include design-fidelity checks.
  • QA verdict is recorded in a test work product when task context exists.
  • Passing QA verdicts cite an external ARTIFACT: marker, not only the model's judgment.
  • QA-required tasks can pass scripts/copilot-gate.sh.

Workflow

  1. Check task and implementation work products when a task exists.
  2. Hydrate config and search memory for prior failures when cc is configured.
  3. Define the behavior under test and acceptance criteria.
  4. Use cc docs get <pkg> when verification depends on installed third-party APIs.
  5. Identify likely regression paths, edge cases, and design-fidelity risks.
  6. Run or write the smallest meaningful tests.
  7. Exercise user-facing flows when UI or workflow behavior changed.
  8. Inspect responsive states, accessibility behavior, visual hierarchy, and product language when product-facing.
  9. Store a test work product with an ARTIFACT: marker and VERDICT: APPROVED, VERDICT: APPROVED-WITH-MINOR-FIXES, or VERDICT: REJECTED.

Output

Return:

  • acceptance criteria
  • tests/checks run
  • design-fidelity checks when product-facing
  • pass/fail verdict
  • uncovered risk

Read the full file on GitHub · 93 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 · 93 lines · 44 tokens per session scan A 20d0789dbae7

Subscribe to this mod's changes

qa is a skill published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (13 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 887 once invoked, about $0.0002 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 2026-09-04.

Related

Other skills, from other repositories

cadence-first

Meta-orchestrator: assigns skill-chain cadence per block (Tier 1/2/3) via Q1-Q6 rules. Reads target taskblocks + task.md, writes cadence-decisions-{R}.md artifact. Standalone (executor invokes) or Batch (generator hand-off). Use when: deciding cadence for a batch of blocks, generator hand-off from decomposition skills.

bearded-illirian/trailmark · 79 tokens

ship-first

Final task completion protocol: report → user-note → deploy → smoke test → close? → guide? → routing.db → propagate → STATUS → sessions. Invoked from fast-track and pipeline flows after task execution, not directly by the user. Use when: invoked after the execute step of a fast-track or pipeline task.

bearded-illirian/trailmark · 68 tokens

ui-ai-first

Final audit of a large task before closure — finds which operations are available only via code / curl / SQL and decides per each: automate with a skill or AI agent (A) or create a UI task (B). Protects against invisible usability debt. Walks through each implemented block: reads task.md + reports + guides + code →…

bearded-illirian/trailmark · 145 tokens

decision-first

Makes an architectural / project / scope decision using a 5-part model INSTEAD of asking the user. Structure: 🎯 Decision / Why / 🛡 Security / 📈 Scalability / Alternatives / Plain-language analogy. 1 question = 1 atomic artifact. Use when: the agent is about to ask an architectural / scope question…

bearded-illirian/trailmark · 89 tokens

library-first

Mandatory protocol before executing any fast-track task. Analyzes the task, builds a table: what we do / where it comes from / how many lines of code. Principle: maximum reuse of existing libraries and components, minimum new code. Waits for explicit user approval — does nothing until confirmed. Use when: fast-track…

bearded-illirian/trailmark · 77 tokens

fixture-new

Creates a parity fixture — the frozen scenario plus the contract its output must satisfy. Asks which skill and case, what shape the run must produce, and writes input.md and expect.yml. Ends by proving the new fixture actually fails on an empty directory. A fixture that passes when nothing ran is worse than no…

bearded-illirian/trailmark · 122 tokens