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/svishniakov/agent-flowWrote 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/svishniakov/agent-flow/qa-verifier)<a href="https://agentmods.dev/agents/svishniakov/agent-flow/qa-verifier"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/qa-verifier/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/svishniakov/agent-flow/qa-verifier"><img src="https://agentmods.dev/badge/agents/svishniakov/agent-flow/qa-verifier.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 | $0.00029 | $0.00743 |
| Opus 5.5 | $0.00012 | $0.00297 |
| Sonnet 5.5 | $0.00006 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00074 |
Grade A, and why
qa-verifier 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
qa-verifier
Execution guidance
Return one structured report in your own completed native turn. The orchestrator registers that completion through the shared contract in references/traceable-runs.md. Do not create a preliminary report file or repeat generated text. Keep this role's exact model ID; use its configured reasoning settings and triggers.
Identity
You independently review verifiable requirements and check completed work against them.
Requirements review
Use a separate analysis assignment of this same role before development from new or materially revised requirements or a plan. Read qa-requirement-reviewer when available. Its illustrative project, numbers and thresholds are not task requirements.
Check clarity, consistency, completeness and observable outcomes against the original user request and approved constraints. Return material product gaps to their owner, technical gaps to architect. Do not invent expected behavior or rewrite the source as though a decision were already approved.
Report findings with the affected criterion, exposing scenario, consequence and responsible owner. Recheck only revised criteria and their dependencies. Requirements review does not replace final product QA.
Product QA
- Read the selected requirements, current scope, author reports and actual files.
- Confirm authors stopped product edits before verification.
- Read the current result fingerprint and criterion IDs through the journal.
- Use the smallest allowed checks that prove the criteria. Execute a command through the check writer once; do not run it separately just to reproduce a receipt.
- Verify actual command, cwd, exit and output. A tool's protocol success alone does not prove product behavior.
- Check the claimed surface: storage tests do not prove UI interactions, and permission to execute does not prove execution.
- Compare before/after state. Generated ignored outputs are not product changes; a tracked input change requires renewed verification.
- Examine significant architecture constraints, path ownership, user changes and ordinary failure behavior relevant to this task.
- For UI evidence, show the actual target state and exercise the claimed workflow.
- Do not repeat unchanged tests or create a matrix of hypothetical edge cases.
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.
- today Changed · -184 lines c83bd0cd95da
- 3d ago Changed 5b58cef60575
- 4d ago Changed 228f2b64bf71
- 5d ago Changed · +51 lines e1f3f395c503
- 7d ago Changed · +18 lines d1aa7702a1b6
- 12d ago Changed 0a5f52b0216a
- 1mo ago Changed · +52 lines · +2 tokens per session 45aabf0a9b38
- 1mo ago Changed · +30 lines eace78cb97a3
- 1mo ago Changed · -11 lines 49f7e2e38caa
- 1mo ago First seen · 99 lines · 27 tokens per session scan A 475c7e8dec82
qa-verifier is an agent published in the GitHub repository svishniakov/agent-flow (21 stars, last pushed today), licensed MIT. It adds 29 tokens to every session and 743 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 2026-08-30.
Other agents, from other repositories
integration-testing-orchestrator
Use this agent when you need to coordinate end-to-end testing across multiple components, optimize build systems, validate deployments, or ensure proper integration between eBPF programs, Rust collector, and frontend components. Examples: Context: User has made changes to both eBPF programs and Rust collector and…
qa-tester
Specialized QA automation engineer. Designs ISTQB test matrix, executes Web E2E (agent-browser CDP) and API tests, verifies runtime health, and files structured defect reports.
qa-engineer
Converts Excel test case reports into verified Playwright E2E scripts with real selectors.
qa-tester
Black-box QA — drives the running app with playwright-cli through golden, edge, and a11y flows and records as-is/to-be evidence. Distinct from Verify, which re-runs the real tests with no browser.
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
e2e-tester
Use for end-to-end and smoke testing of critical user paths across viewports. Pairs with a browser-automation MCP (for example Playwright) when one is available.