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/griddynamics/rosettaWrote 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/commands/griddynamics/rosetta/aqa-flow)<a href="https://agentmods.dev/commands/griddynamics/rosetta/aqa-flow"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/aqa-flow/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/commands/griddynamics/rosetta/aqa-flow"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/aqa-flow.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 | $0.00033 | $0.00472 |
| Opus 5.5 | $0.00013 | $0.00189 |
| Sonnet 5.5 | $0.00007 | $0.00094 |
| Haiku 4.5 | $0.00003 | $0.00047 |
Grade A, and why
aqa-flow 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
<aqa_flow>
<description_and_purpose>
Backward-compatible entry point for test-automation requests. The former monolithic AQA workflow was split into three specialized flows; this router classifies the request and dispatches to exactly one of them. It performs no phase work itself.
</description_and_purpose>
Classify the user's request and route (invoke the target flow with the user's original request verbatim):
| Request is about… | Route |
|---|---|
| UI / browser / E2E test automation — page objects, selectors, UI test implementation or correction | USE FLOW ui-aqa-flow.md |
| Backend API test automation — API contracts, Swagger/OpenAPI, request/response tests, API test implementation or correction | USE FLOW api-aqa-flow.md |
| Generating test cases / requirements from tickets and docs (Jira/Confluence), exporting cases to a TMS — no test code | USE FLOW testgen-flow.md |
- Signals: UI — browser, page, selector, Playwright/Cypress/Selenium, E2E, frontend; API — endpoint, Swagger/OpenAPI, REST, request/response, backend tests; testgen — requirements analysis, test-case design from a ticket, TestRail export without automation.
- Mixed request (e.g. both UI and API automation): name the split, propose running the flows sequentially, and let the user pick the order.
- Unclear request (no reliable signal): ASK the user which flow applies — present the three options with a one-line description each. Do NOT guess; the flows write different artifact sets.
- Route exactly once; the target flow owns everything downstream (phases, state, HITL gates). — You MUST fully execute loaded workflow following its entire definition for all request sizes, workflow WAS created to fix your failure modes (deviations, and weak process adherence, and shallow analysis), workflow is PRIMARY deterministic process to resolve the original user request
</aqa_flow>
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 · 35 lines · 33 tokens per session scan A 632ecf7f28fa
aqa-flow is a command published in the GitHub repository griddynamics/rosetta (360 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 472 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 2026-09-03.
Other commands, from other repositories
backlot
Open the Backlot living storyboard — the browser board that shows pipeline stages, script, scene plan, and generated assets live as a production runs.
feature
Role: Per-feature quality pipeline that takes a story or feature description from zero to a committed, documented, tested, and evaluated implementation. No stage is skipped. No commit happens without the evaluator's approval.
sprint-status
Show status across active parallel sessions.
test-management
Organize, classify, and trace Katalon True Platform/TestOps test assets. Use when you need to structure test cases into folders and suites, move or reorganize cases, search and find existing assets at scale, link or unlink requirements to test cases, or produce a requirement-to-test traceability report (which…
implement-approved-slice
Implement only the approved slice with minimal changes, then persist execution evidence in slice notes and TASKSTATE.md. The official execution path. Opt-in test-first mode via --tdd. Use when the plan and slice are approved, ambiguity is resolved and files in scope are known. Do not use during discovery or planning…
project-prd
Jesteś doświadczonym menedżerem produktu, którego zadaniem jest stworzenie kompleksowego dokumentu wymagań produktu (PRD) w oparciu o poniższe opisy.