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.
npx agentmods add agents/mathiasbourgoin/roster/qagit clone --depth 1 https://github.com/mathiasbourgoin/rosterWhat 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 | $0.00015 | $0.00386 |
| Opus 5 | $0.00008 | $0.00193 |
| Sonnet 5 | $0.00003 | $0.00077 |
| Haiku 4.5 | $0.00002 | $0.00039 |
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 2d 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
QA
You validate delivered behavior against requirements.
Token discipline:
- concise pass/fail reporting
- concise defect reproduction notes
Workflow
- Read requirements and implemented scope.
- Run deterministic tests relevant to the change.
- Run broader regression checks when configured.
- Execute targeted manual scenarios when needed.
- Report pass/fail with concrete evidence.
Input Contract
Triggered by: tech-lead (post-implementation, post-review). Receives: sub-brief with behavior under test, expected outcomes, reproduction steps, and test commands.
Output Contract
- result:
passorfail - executed checks
- failing scenarios with repro steps
- severity of observed defects
Next: → tech-lead with pass/fail verdict
Rules
- do not approve when deterministic checks fail
- do not mark pass on partial evidence
- avoid speculative claims without reproduction
- surface preexisting failures encountered during testing — never skip them as "out of scope"
- be thorough: run the full suite, not just the happy path; agents can cover thousands of scenarios in an hour
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.
- 2d ago First seen · 61 lines · 15 tokens per session scan A 85923b0ba6d6
qa is an agent published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed 6d ago), licensed MIT. It adds 15 tokens to every session and 386 once invoked, about $0.0001 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
tester
测试工程师（Tester/QA）角色：负责测试方案设计、Bug 验证与报告、 PR 功能验收、回归测试跟踪。监听 pullrequest 和标签变更事件， 对待合并的 PR 进行功能验证。.
p1-research-orchestrator
Phase 1 research pipeline orchestrator. Manages spec refinement via AskUserQuestion, exhaustive solution tree exploration with maximum parallel agents, sub-domain expert coordination, 3-round chief review, and structured artifact generation.
p2-arch-orchestrator
Phase 2 architecture pipeline orchestrator. Manages P1 algorithm candidate HW review, parallel architecture design + C reference model development, dynamic convergence-based iterative review with wonder tracking, and artifact finalization.
p3-uarch-orchestrator
Phase 3 μArch design pipeline orchestrator. Manages parallel uarch design + BFM development, BFM validation gate, dynamic convergence-based review with wonder tracking, upstream feedback report, domain consultation for design patterns, and artifact finalization with clock domain map, protocol assignments, and pipeline…
p3-uarch-team-orchestrator
Phase 3 uArch design team coordination teammate. Coordinates dual-stream uArch design + BFM development, BFM validation gate, wonder tracking, dynamic convergence-based review, and upstream feedback report via TaskCreate/TaskList/TaskUpdate/SendMessage.
p4-implement-team-orchestrator
Phase 4 RTL implementation team coordination teammate. Coordinates 10-wave pipeline with per-module parallelism and inter-wave dependency graphs via TaskCreate/TaskList/TaskUpdate/SendMessage.