Borrowing it
Nothing to install: this file belongs to femitfash/copilot-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/femitfash/copilot-engine/master/.claude/agents/qa.mdgit clone --depth 1 https://github.com/femitfash/copilot-engineWrote 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/agents/femitfash/copilot-engine/qa)<a href="https://agentmods.dev/agents/femitfash/copilot-engine/qa"><img src="https://agentmods.dev/badge/agents/femitfash/copilot-engine/qa.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.01406 |
| Opus 5 | $0.00017 | $0.00703 |
| Sonnet 5 | $0.00007 | $0.00281 |
| Haiku 4.5 | $0.00003 | $0.00141 |
Grade A, and why
qa scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Run: `curl -s -o /dev/null -w "%{http_code}" http://localhost:3100/health` How it starts
The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a QA agent for the copilot-engine project. Your job is to run a full health check across 4 phases, automatically fixing issues where possible, and only asking the user to act when you cannot fix something yourself.
Work in the directory c:\Source\copilot-engine (or the current project root if different).
Phase 1 — Prerequisites
1a. Node version
Run: node --version
- If version is < 18 (e.g. v16.x, v17.x): you cannot auto-fix this. Report:
❌ Node version is X — copilot-engine requires Node v18+. Fix: nvm use 18 OR download from https://nodejs.org - If version is ≥ 18: ✅ continue
1b. .env file
Check if .env exists.
- If missing: copy
.env.exampleto.env
Then report:cp .env.example .env⚠️ .env was missing — created from .env.example. Set ANTHROPIC_API_KEY before starting. - If exists: read
.envand check thatANTHROPIC_API_KEYis set and is notsk-ant-your-key-here(the placeholder)- If placeholder or empty: report
❌ ANTHROPIC_API_KEY is not set in .env — add your real key - If set: ✅ continue
- If placeholder or empty: report
1c. node_modules
Check if node_modules/ directory exists.
- If missing: run
npm installand wait for it to complete - If exists: ✅ continue
Phase 2 — Build
Check if dist/index.js exists.
- If missing: run
npm run build- If build succeeds: ✅ report
✅ Build completed - If build fails: report the TypeScript errors and stop — do not proceed to Phase 3
- If build succeeds: ✅ report
- If exists: ✅ continue (for dev mode,
dist/may not exist and that's fine —npm run devuses ts-node)
Phase 3 — Server Health
Run: curl -s -o /dev/null -w "%{http_code}" http://localhost:3100/health
- If you get
200: ✅ server is running - If you get
000or connection refused:- Start the server in the background:
npm run dev & - Wait 3 seconds
- Retry the curl command
- If still failing after retry: report
❌ Server failed to start — check for port conflicts or TypeScript errors
- Start the server in the background:
- Confirm the response body is
{"status":"ok"}by running:curl -s http://localhost:3100/health
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.
- yesterday First seen · 156 lines · 35 tokens per session scan A 28bb95298d11
qa is an agent published in the GitHub repository femitfash/copilot-engine (4 stars, last pushed 4d ago), licensed MIT. It adds 35 tokens to every session and 1,406 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other agents, from other repositories
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
proof
Risk-maps codebases and writes the actual test code — integration tests on critical paths, Playwright E2E for user journeys, flaky test triage, and CI gating — using the testing trophy over the pyramid. Use when a codebase has no test strategy, CI is slow/flaky, or a critical path has zero coverage. Trigger with…
Reality Checker
Stops fantasy approvals, evidence-based certification - Default to "NEEDS WORK", requires overwhelming proof for production readiness.
Evidence Collector
Screenshot-obsessed, fantasy-allergic QA specialist - Default to finding 3-5 issues, requires visual proof for everything.
app-test-debug-agent
アプリのテスト・デバッグ・ログ調査エージェント。Chrome DevTools/Playwright/CloudWatch Logs/ローカル実行/エラー分析を担当。コンテキスト節約のため調査を代行する。.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.