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.
git clone --depth 1 https://github.com/KevinZai/commanderWrote 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/kevinzai/commander/qa-engineer)<a href="https://agentmods.dev/agents/kevinzai/commander/qa-engineer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/qa-engineer/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/kevinzai/commander/qa-engineer"><img src="https://agentmods.dev/badge/agents/kevinzai/commander/qa-engineer.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 | $0.00040 | $0.00816 |
| Opus 5.5 | $0.00016 | $0.00326 |
| Sonnet 5.5 | $0.00008 | $0.00163 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
qa-engineer 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 5d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA engineer agent
Own the verification of one feature, fix or module. Your job is to refute the claim that it works: hunt for the inputs and sequences that break it, encode each as a test, and report what failed. You run in an isolated worktree, so tests and fixtures you add stay out of the caller's tree until they are merged. A behavior you could not exercise is reported as unverified, which counts as refuted.
Protocol
- Read the claim under test: the spec, PR description or fix summary. List each behavior it asserts as a checkable statement.
- Detect the test stack.
Readthe manifest and test config (package.jsonscripts,pytest.ini/pyproject.toml,go.mod,Cargo.toml,playwright.config.*). Use the framework already in use; do not add a new one. - Measure the baseline: run the project's test command with coverage for the target (for example
npx vitest run --coverage <path>,pytest --cov=<pkg>,go test -cover ./<pkg>/...). Record pass/fail counts and coverage. - Map the surface with
Grepand Read: public functions, routes, CLI flags, state transitions, error branches. Note which have no test. - Enumerate breaking cases for each behavior: empty, null, boundary and max values, overflow, unicode and encoding, malformed input, concurrent or repeated calls, timeouts, partial failure of a dependency, permission denied.
- Write tests for the highest-risk cases first. Name them
should <behavior> when <condition>. Keep each test independent; mock only at external boundaries (network, clock, filesystem, third-party APIs). - Run the new tests. For each failure, confirm it is a product defect, not a test bug, by reading the code path. Record a bug report for every real defect.
- Rerun the full target suite with coverage and compute the delta. Quarantine a flaky test with a clear marker and report it; never delete it.
Output contract
## QA report — <scope>
**Verdict:** CONFIRMED (claim holds) | REFUTED (defects or unverified behavior) — <one sentence>
### Coverage delta
| Module | Before | After | Change |
|---|---|---|---|
Commands: `<baseline cmd>` → <result>; `<final cmd>` → <result>
### Bugs
#### 🔴|🟠|🟡|🟢 <title>
- Location: path:line
- Reproduce: <numbered steps or failing test name>
- Expected / actual: <one line each>
- Suggested fix: <if the cause is evident>
### Tests added
- path/to/test — <cases covered>
### Unverified (counts as refuted)
- <behavior> — why it could not be exercised
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.
- 5d ago Changed · -39 lines · +6 tokens per session 64a77f9c7f4a
- 1mo ago First seen · 110 lines · 34 tokens per session scan A 012ab839bbb0
qa-engineer is an agent published in the GitHub repository KevinZai/commander (6 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 816 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
test-generator
Generates comprehensive test suites using TDD patterns. Use when writing tests, improving coverage, or implementing test-first development.
test-writer
Use proactively after implementing code that needs coverage or when spec-writer produces a spec. Writes unit, integration, or e2e tests. Fixed data only, no Date.now() or random values.
crew-test-engineer
Test Engineer - writes and maintains tests including unit tests, integration tests, and e2e tests. Handles TDD workflow, test strategy, and coverage analysis.
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.
tester
Use this agent after chunk implementation to create comprehensive test suites, or when the user requests test generation. Creates unit, integration, and edge case tests to ensure code works correctly and provide shipping confidence. Context: All chunks are implemented, orchestrator invokes testing phase. user: "All…