ui-aqa-flow

ui-aqa-flow is a command for coding agents from griddynamics/rosetta. It costs 24 tokens per session (2,990 once invoked), scanned A, original, Apache-2.0.

Workflow for automated QA: integration and end-to-end UI test automation, page objects, etc.

Command

Install

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.

agentmods
npx agentmods add commands/griddynamics/rosetta/ui-aqa-flow
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta

Wrote 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.

agentmods badge for ui-aqa-flow

README.md
[![agentmods](https://agentmods.dev/badge/commands/griddynamics/rosetta/ui-aqa-flow.svg)](https://agentmods.dev/commands/griddynamics/rosetta/ui-aqa-flow)
Your own site
<a href="https://agentmods.dev/commands/griddynamics/rosetta/ui-aqa-flow"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/ui-aqa-flow.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,990 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00024 $0.02990
Opus 5 $0.00012 $0.01495
Sonnet 5 $0.00005 $0.00598
Haiku 4.5 $0.00002 $0.00299

Measured today against content hash c9d6a4df65de, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ui-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 today.

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.

plugins/core-copilot-light/commands/ui-aqa-flow.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<ui_aqa_flow>

<description_and_purpose>

End-to-end test automation from requirements gathering to test implementation. Uses test cases, project documentation to create automated tests following existing architecture and coding standards.

Prerequisite: Rosetta Prep Steps.

Terminology. External systems are named by role throughout this workflow and its phases: Test Management System (TMS), Issue Tracker, and Wiki. TestRail, Jira, and Confluence are canonical examples only — adapt identifiers, URLs, requests, calls, and query syntax to the systems resolved for the current project (from repository-root gain.json, explicit user input, recognizable URLs/handles, and available integrations).

</description_and_purpose>

<workflow_phases>

Execution cadence:

  • All Rosetta prep steps MUST be FULLY completed
  • USE SKILL load-project-context, orchestration, hitl
  • MUST ALWAYS use todo tasks ledger, ASAP. Phases are sequential. Independent tasks can run in parallel.
  • Execute every in-scope phase in strict 1-8 order (never skip without explicit HITL confirmation): APPLY PHASE the phase file → update agents/TEMP/<FEATURE>/ui-aqa-state.md → next; never start a phase until the previous is marked done in ui-aqa-state.md.
  • MUST follow JIT phase-by-phase: do not load/act IN ADVANCE.
  • Skip gates, transitions, and escalation → <orchestration_and_escalation>.
  • MUST ALWAYS use todo tasks ledger, ASAP. Prioritize ACCURACY over SPEED. Proactively use available tools/MCPs, if question can be answered from code or MCP call - do that first.

No assumptions:

  • NO ASSUMPTIONS: never assume selectors, flows, or data — ask the user when information is missing.

Customization:

  • If the user gave no preferences, perform all steps except optional.
  • User CAN customize specific phases / already-done phases / goals / cases — LISTEN and ADOPT.

Authoritative rules (do not skim past):

  • USE SKILL coding before any work touching repository tests, page objects, or shared helpers — authoritative for conventions; repository docs win over skill snippets.
  • Default: reuse existing page objects/tests first; create new files only when no suitable match exists.
  • Explicit assertions: every test validation traces to a requirement — owned by Phase 2 (### Explicit Assertions in the test plan), enforced when Phase 6 implements tests.
  • Blocking infeasibility = HARD-STOP + HITL (NOT waived by a clarification skip): if any phase finds the feature/elements under test do not exist such that the test cannot be authored without inventing selectors/flows/data or modifying product source, STOP and escalate with the options — point at the real feature/URL · author the missing UI as a separate approved task · a clearly-marked pending/fixme spec · abort — and WAIT for the user's explicit choice. "Skip clarification" waives clarification questions only; it never authorizes this feasibility/scope call.

<data_collection phase="1" applies="ALL" subagent="discoverer" role="UI-AQA data collector" subagent_required_model="Claude Sonnet 5, GPT-5.6 Terra, Gemini 3.7 Flash">

  • APPLY PHASE ui-aqa-flow-data-collection.md
  • Input: user request + repository-root gain.json + project context at its configured paths (canonical: docs/CONTEXT.md, docs/ARCHITECTURE.md, agents/IMPLEMENTATION.md). Output: test plan at plans/ui-aqa-<test-name>/test-plan.md
  • Required skills: data-collection, sensitive-data, qa-structure, qa-knowledge
  • Update agents/TEMP/<FEATURE>/ui-aqa-state.md; Phase 1 is not complete until its output spot-check passes. </data_collection>

<requirements_clarification phase="2" applies="ALL" subagent="architect" role="Test requirements analyst" subagent_required_model="Claude Opus 5, GPT-5.6 Sol, Gemini 3.7 Flash" type="HITL">

  • APPLY PHASE ui-aqa-flow-requirements-clarification.md
  • Input: user request + collected data from Phase 1. Output: clarified requirements + typed assertion list in the test plan
  • WAIT FOR USER ANSWERS to the clarifying questions before Phase 3.
  • Required skills: qa-knowledge (gap_analysis mode), qa-structure
  • Recommended skills: questioning
  • Update agents/TEMP/<FEATURE>/ui-aqa-state.md; Phase 2 is not complete until its output spot-check passes. </requirements_clarification>

Read the full file on GitHub · 142 lines

Changes

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.

  1. today First seen · 142 lines · 24 tokens per session scan A c9d6a4df65de

Subscribe to this mod's changes

ui-aqa-flow is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 24 tokens to every session and 2,990 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 2026-09-03.