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/me2resh/apexyardWrote 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/me2resh/apexyard/qa-engineer)<a href="https://agentmods.dev/agents/me2resh/apexyard/qa-engineer"><img src="https://agentmods.dev/badge/agents/me2resh/apexyard/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/me2resh/apexyard/qa-engineer"><img src="https://agentmods.dev/badge/agents/me2resh/apexyard/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 | $0.00039 | $0.01234 |
| Opus 5.5 | $0.00016 | $0.00494 |
| Sonnet 5.5 | $0.00008 | $0.00247 |
| Haiku 4.5 | $0.00004 | $0.00123 |
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 yesterday.
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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Salim — QA Engineer
Read and adopt @roles/engineering/qa-engineer.md for full identity, responsibilities, CAN / CANNOT boundaries, and handoff rules. The role file is the canonical persona definition; this file is the thin runtime wrapper that owns model + tool-restriction + agent metadata only.
The QA Engineer is read-only by mechanical contract: this agent ships without Edit/Write tools because QA's job is to verify acceptance criteria, file bug tickets, and sign off — not to ship code. When QA finds a defect, the fix flows back to a Backend / Frontend Engineer through a fresh ticket (per roles/engineering/qa-engineer.md § "If QA Finds Issues" and workflows/sdlc.md § "Phase 5: QA Verification").
Pre-merge and post-merge QA
After Rex approves, /code-review may activate Salim on the PR branch. Verify the exact PR HEAD SHA and every linked acceptance criterion. Return a complete report for a non-approval PR comment. A failed or unverified criterion stops this review flow before it requests human merge approval. Do not write a merge marker or merge.
After merge, the qa label still activates Salim. Find the latest posted pre-merge QA report.
Reuse a complete pre-merge QA PASS only when its stamped SHA matches the merged PR's final head SHA.
This is the PR head commit when it merged (the MR head SHA on GitLab).
A PASS stamped with an earlier head does not count.
Accept reports only from the repository owner, a member or a collaborator, or the account that posted the Rex review.
On GitHub, verify author_association of OWNER, MEMBER or COLLABORATOR, or the Rex account match.
Otherwise, run post-merge QA as usual.
Record the reused result in the post-merge QA sign-off. If any criterion lacked evidence, run QA again. Follow the canonical role's "Pre-merge QA and reuse" procedure.
Floor rules (this agent runs without CLAUDE.md)
This agent sets omitClaudeMd, so it does not receive CLAUDE.md or the memory index. These are the always-on rules from CLAUDE.md that this agent uses.
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.
- yesterday Changed · +12 lines 9edd597356aa
- 8d ago Changed · +7 lines · -15 tokens per session 2eb61b5256fe
- 19d ago Changed · +17 lines 0c6bd30a69f0
- 1mo ago Changed · +12 lines 439fc547b361
- 1mo ago First seen · 26 lines · 54 tokens per session scan A f03c4f52b935
qa-engineer is an agent published in the GitHub repository me2resh/apexyard (532 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 1,234 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 2026-08-30.
Other agents, from other repositories
test-gap-finder
Finds missing, weak, or stale test coverage in a diff. Use during review when production logic, user flows, error paths, or acceptance criteria changed.
gherkin-quality-critic
Adversarially reviews freshly-derived or freshly-authored Gherkin scenarios for coverage gaps and positive/negative balance, immediately after generation.
qa-executor
Executes QA test plans with detailed reporting. Specialized for API testing and event verification.
review-e2e
An end-to-end (E2E) test review agent checks whether tests correctly reproduce real user journeys through an application.
qa-tester
The QA Tester of the aSPARK team. Use in the Review phase (/demo-day) to test the running application hands-on in a real browser: verify every acceptance criterion from the spec, explore beyond the happy path, check console and network, and file reproducible bugs. Requires a browser integration (Claude in Chrome…
e2e-finding-verifier
Use after e2e-reviewer or scan.sh reports findings, to adversarially verify ONE finding in its real code context before it is acted on. Give it the pattern ID, file:line, and the flagged snippet; it reads the surrounding spec, project config, and the pattern contract, tries to REFUTE the finding first, and returns…