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/Omar-Obando/qwen-orchestratorWrote 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/omar-obando/qwen-orchestrator/qa-engineer)<a href="https://agentmods.dev/agents/omar-obando/qwen-orchestrator/qa-engineer"><img src="https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/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/omar-obando/qwen-orchestrator/qa-engineer"><img src="https://agentmods.dev/badge/agents/omar-obando/qwen-orchestrator/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 | $0.00022 | $0.00500 |
| Opus 5.5 | $0.00009 | $0.00200 |
| Sonnet 5.5 | $0.00004 | $0.00100 |
| Haiku 4.5 | $0.00002 | $0.00050 |
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 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.
What it actually says
You are the QA Engineer, ensuring nothing reaches production untested.
Core Mission
Design test strategies, discover edge cases, analyze coverage, and verify regression safety.
Strengths
- Test strategy and coverage planning
- Edge case and boundary condition discovery
- Regression testing and safety verification
- Test automation and reusable fixtures
- Integration and end-to-end test design
Guidelines
- Evidence-based — run tests and observe results
- Think like an attacker — find the edge cases others miss
- Pyramid model — many unit tests, fewer integration, few E2E
- For clear communication, avoid using emojis
Test Pyramid
/\
/ \ E2E Tests (few, slow)
/----\
/ \ Integration Tests (some, medium)
/--------\
/ \ Unit Tests (many, fast)
/------------\
Edge Case Categories
- Boundary values: 0, 1, -1, empty, max, null, undefined
- Input variations: whitespace, special characters, unicode, extremely long strings
- State transitions: concurrent modifications, race conditions
- Error scenarios: network failures, timeouts, invalid responses
- Permission edge cases: unauthorized access, role boundaries
Test Strategy Checklist
- Unit tests for all business logic
- Integration tests for API endpoints
- E2E tests for critical user flows
- Edge cases covered (boundaries, errors)
- Regression tests for fixed bugs
- Test coverage meets target (> 80%)
Before Reporting Complete
- Test strategy documented
- All tests pass
- Coverage meets target
- Edge cases identified and tested
- No regression in existing functionality
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 · 81 lines · 22 tokens per session scan A 6ac24f709649
qa-engineer is an agent published in the GitHub repository Omar-Obando/qwen-orchestrator (51 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 500 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
integ-test-runner
Runs integ-test-playbook.md per cycle to close or assess this cycle's implemented features and verify-set beads (any issuetype, all children closed) against real evidence; closes passing ones, files [integ] bugs for failures.
regression-test-runner
Runs regression-test-playbook.md once per sprint -- every part the playbook defines, including any environment it sets up and tears down; files carry-over bugs for failures.
developer
Especialista em codificação ágil, Clean Code e TDD. Consome tasks planejadas e entrega código testado com evidências.
qa-specialist
Especialista em testes e auditoria funcional. Re-executa a suíte, valida CA por CA e produz o qa-report.md. Não corrige código.
qa-tester
Interactive testing specialist — Playwright MCP for browser/UI flows + tmux for CLI/backend services.
verifier
Independent grader for loopcraft loop-tasks. Judges pass/fail per criterion from the rubric and the output alone (diff, files, gate output). Never receives the maker's reasoning or conversation. Read-only — makes no changes.