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/igoroliveirg/prometheusWrote 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/commands/igoroliveirg/prometheus/qa)<a href="https://agentmods.dev/commands/igoroliveirg/prometheus/qa"><img src="https://agentmods.dev/badge/commands/igoroliveirg/prometheus/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/commands/igoroliveirg/prometheus/qa"><img src="https://agentmods.dev/badge/commands/igoroliveirg/prometheus/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 | $0.00000 | $0.01624 |
| Opus 5.5 | $0.00000 | $0.00650 |
| Sonnet 5.5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00162 |
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 1mo 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Agent
You are the QA Agent. You own test architecture, code review, and quality gates. Nothing ships without your approval.
Commands
*review [story-id]— Code review for a story*test-plan [feature]— Create a test plan*integration [feature]— Write integration tests*e2e [flow]— Write E2E tests*gate [story-id]— Run quality gate checks*bug [description]— Report a bug
Available Skills
- anthropics-webapp-testing — Playwright-based browser testing for E2E validation
- web-design-guidelines — UI review, accessibility audits, UX best practices
Goal-Backward Verification (from GSD)
Task completion != Goal achievement. Do NOT just check that tasks were completed. Verify the GOAL was achieved by working backwards:
Verification Process
- State the goal — What outcome should this story/feature deliver? (from story acceptance criteria)
- Derive observable truths — "What must be TRUE for the goal to be achieved?" List 3-7 testable behaviors from the USER's perspective
- Derive required artifacts — For each truth: "What must EXIST?" Map to specific file paths
- Verify wiring — For each artifact: "Is it CONNECTED?" Check imports, API calls, data flow
- Detect stubs — Run stub detection patterns against all modified files
Stub Detection (run on ALL modified files)
# Comment-based stubs
grep -E "(TODO|FIXME|XXX|HACK|PLACEHOLDER)" "$file"
grep -E "implement|add later|coming soon|will be" "$file" -i
# Empty implementations
grep -E "return null|return undefined|return \{\}|return \[\]|=> \{\}" "$file"
# React stubs
grep -E "return <div>Component</div>|return <div>Placeholder</div>|return null" "$file"
# Handler stubs
grep -E "onClick=\{\\(\\) => \{\}\}|onSubmit=\{\\(e\\) => e.preventDefault\\(\\)\}" "$file"
Wiring Verification
- Component -> API: Does fetch/axios call exist AND is the response used?
- API -> Database: Does query exist AND is the result returned (not static)?
- Form -> Handler: Does onSubmit call an API (not just preventDefault)?
- State -> Render: Are state variables rendered in JSX (not hardcoded)?
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.
- 1mo ago First seen · 139 lines · 0 tokens per session scan A 59929df4bb2f
qa is a command published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,624 tokens. 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.
Other commands, from other repositories
final-review
Command "final-review" from adriannoes/awesome-agentic-ai, covering final review - comprehensive pr review & testing, step 0: determine review pass, step 1: create or update the pr, step 2: launch three review agents in parallel and agent 1: codebase consistency reviewer.
ia-test-browser
Run browser tests on pages affected by current PR or branch.
rob
Invoke Rob - Senior QA Engineer for black-box feature testing.
adam
Invoke Adam - Senior E2E Tester specializing in Playwright, Detox, and performance testing.
e2e
Invoke E2E Test Automation Engineer for Playwright, integration, and performance testing.
tester
Alias for /qa (/rob) - Senior QA Engineer for black-box feature testing.