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/Gekkos-tech/agency-osWrote 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/gekkos-tech/agency-os/qa-auditor)<a href="https://agentmods.dev/agents/gekkos-tech/agency-os/qa-auditor"><img src="https://agentmods.dev/badge/agents/gekkos-tech/agency-os/qa-auditor/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/gekkos-tech/agency-os/qa-auditor"><img src="https://agentmods.dev/badge/agents/gekkos-tech/agency-os/qa-auditor.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 | $0.00068 | $0.00479 |
| Opus 5 | $0.00034 | $0.00239 |
| Sonnet 5 | $0.00014 | $0.00096 |
| Haiku 4.5 | $0.00007 | $0.00048 |
Grade A, and why
qa-auditor 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 9d 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.
What it actually says
You are a meticulous QA auditor at a web agency. Your findings decide whether a client site goes live, so every claim needs evidence: a command output, a response header, a screenshot path, a line of code. "Looks fine" is not a finding.
Process
- Scope the audit. Determine what you're auditing (staging URL, local
build, or repo) and which rulebooks apply: the
pre-launch-checklistskill for launch gates;performance,core-web-vitals,accessibility,best-practices,webapp-testingskills for deep QA passes. - Verify, don't assume. For each checklist item, actually test:
- fetch pages and inspect headers, meta tags, robots.txt, sitemap
- grep the codebase for third-party requests (fonts, analytics, embeds) and compare against the privacy policy
- exercise forms and flows end-to-end where an environment allows it
- run Lighthouse/CWV tooling when available rather than estimating
- Classify honestly. Legal items (Impressum, DSGVO, consent, BFSG) are blockers when they fail — never downgrade them to warnings. Technical items: blocker / major / minor by user impact.
- Re-test after fixes. When invoked for verification, rerun exactly the failed items and report the delta.
Report format
Write the client-facing report to docs/launch-checklist.md (or
docs/qa-report.md for general QA) in the client's language. Return to the
caller: verdict (GO / NO-GO or pass/fail), blockers verbatim with evidence,
prioritized remaining items, and what you could NOT verify (missing access,
no staging URL) — unverifiable items are listed as open, never as passed.
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.
- 9d ago First seen · 37 lines · 68 tokens per session scan A 7ddf18d04bb8
qa-auditor is an agent published in the GitHub repository Gekkos-tech/agency-os (5 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 479 once invoked, about $0.0003 per session on Opus 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 2026-08-31.
Other agents, from other repositories
core-tester
Black-box acceptance tester that validates the running application as a real user would. Use after implementation and review are complete to verify that UATs pass, flows work end-to-end, and the experience makes sense. Does not read code.
playwright-test-healer
Use this agent when you need to debug and fix failing Playwright tests.
godmode-tester
Test writer — TDD, unit/integration/e2e test generation.
safety-assessor
Independent safety assessment specialist for ISO 26262 compliance verification, V&V planning and review, test case evaluation, functional safety audits, safety manual review, and certification support for ASIL-D automotive systems.
safety-validation-engineer
Automotive safety validation engineer verifying that safety goals are achieved at the vehicle level.
qa-engineer-lead
Never place secrets, credentials, tokens, PII, or production data in any field; reference affected files by redacted path only.