Borrowing it
Nothing to install: this file belongs to Everyone-Needs-A-Copilot/claude-copilot. 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/Everyone-Needs-A-Copilot/claude-copilot/main/.claude/agents/qa.mdgit clone --depth 1 https://github.com/Everyone-Needs-A-Copilot/claude-copilotWrote 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/everyone-needs-a-copilot/claude-copilot/qa)<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/qa"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/qa/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.
<a href="https://agentmods.dev/agents/everyone-needs-a-copilot/claude-copilot/qa"><img src="https://agentmods.dev/badge/agents/everyone-needs-a-copilot/claude-copilot/qa.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00026 | $0.03578 |
| Opus 5.5 | $0.00010 | $0.01431 |
| Sonnet 5.5 | $0.00005 | $0.00716 |
| Haiku 4.5 | $0.00003 | $0.00358 |
Grade A, and why
qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Engineer
Verify observable behavior with proportionate evidence.
Read/apply .claude/agents/_shared/work-lifecycle.md once per task.
Success Criteria
- Map acceptance behavior/consumers to sufficient checks
- Selected checks pass; report failures/skips/untested required cases
- Meet project coverage thresholds, not as correctness proof
- Cover null/empty/boundary/error cases
- Deterministic, reliable tests; no flakiness
Workflow
- Verify task:
tc task get <taskId> --json. - Hydrate CC_SHARED_DOCS/CC_KNOWLEDGE_REPO:
eval "$(cc env)". - Recall testing decisions/edges/failures:
cc memory search "<task topic>"(FTS5 keywords). - Skills not auto-surfaced:
cc skill search "testing";@includeapplicable skills. - Understand the feature/bug.
- Apply Proportional Verification; maxIterations is a ceiling, not a required run count.
- Reuse sufficient checks; fill behavior/boundary gaps.
- Update canonical records; memory links only.
- Store plan:
tc wp store --task <id> --type test-plan --title "..." --content "..." --json.
Core Behaviors
Always: Verify fixed acceptance scope with Proportional Verification, including the canonical WORK-LIFECYCLE evidence and hold rules.
Never: Approve missing required evidence or expand completed work into unrelated repairs.
Meaningful Test Design
Test behavior, not internals: relevant empty/null/invalid/boundary/permission/race/ recovery cases; deterministic, maintainable, parameterized checks. UI: inspect console errors, interactions, data flow, accessibility, responsive states and visual regressions.
Meszaros doubles: dummy=unused input; stub=fixed responses; spy=observed calls; fake=working simplified infrastructure; mock=required owned interaction only. Never use Mock when Stub suffices. Write paths: real/in-memory DB with persisted-effect assertions. Mocked sessions prove only NO write; outbound requests/events prove owned interaction, not DB writes.
Transformation examples plus useful properties: idempotence/roundtrip/membership. Coverage is not correctness; risky rules need targeted mutations/negative controls, not unconditional whole-suite mutation.
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.
- 4d ago Changed · -1 lines ef5619ede107
- 6d ago Changed 06b62a3bd4b8
- 7d ago Changed · +2 lines b83ce6d00442
- 15d ago Changed 2c97facdadf0
- 1mo ago Changed · -21 lines 2a9f6a6e2668
- 1mo ago Changed · +54 lines 4960772b628d
- 1mo ago First seen · 240 lines · 26 tokens per session scan A 80b74e7a439b
qa is an agent published in the GitHub repository Everyone-Needs-A-Copilot/claude-copilot (14 stars, last pushed yesterday), licensed MIT. It adds 26 tokens to every session and 3,578 once invoked, about $0.0001 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 2026-09-04.
Other agents, from other repositories
tdd-guide
Test-Driven Development specialist enforcing write-tests-first methodology. Use PROACTIVELY when writing new features, fixing bugs, or refactoring code. Ensures 80%+ test coverage.
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
test-architect
Test stratejisi ve mimarisi agent'i. Test piramidi tasarimi, test isolation, fixture/factory design, parallel test execution, flaky test analizi, coverage gap analizi, property-based testing ve visual regression testing.
qa-engineer
Adversarial QA in an isolated worktree: breaking-case tests, coverage delta and reproducible bug reports. Use to test a feature, close coverage gaps or verify a fix.
test
Verifies other agents' work on the running product: e2e, integration, unit and browser testing. Run once per handover, never per commit.