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 commands/griddynamics/rosetta/ui-aqa-flow-test-report-analysisgit 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/ui-aqa-flow-test-report-analysis)<a href="https://agentmods.dev/commands/griddynamics/rosetta/ui-aqa-flow-test-report-analysis"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/ui-aqa-flow-test-report-analysis.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.02002 |
| Opus 5 | $0.00010 | $0.01001 |
| Sonnet 5 | $0.00004 | $0.00400 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade A, and why
ui-aqa-flow-test-report-analysis 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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<ui_aqa_flow_test_report_analysis>
<description_and_purpose> Analyze test execution reports, identify failure root causes, and prepare for corrections in Phase 8. </description_and_purpose>
<workflow_context>
- Phase 7 of 8 in
ui-aqa-flow. - Input: test report or execution output + test plan + page sources at
plans/ui-aqa-<test-name>/page-sources/. - Output artifact path (single SSoT — referenced by other sections):
plans/ui-aqa-<test-name>/failure-analysis.md(resolve<test-name>perqa-structure). - Prerequisite: Phase 6 complete, test executed by user.
- HITL: may need to ask user for report location.
- Read-only scope (single SSoT — referenced by other sections as "the read-only scope"): parse / categorize / root-cause / label evidence / recommend. NO production code edits, NO writes to test or product source files. Refuse "just fix it now" / "patch the selector before Phase 8" with citation of this scope; the only acceptable user inputs are report location, evidence/labeling clarifications, or explicit approval to leave borderline items as
Assumption. - Required skills:
qa-knowledge(test_execution_triagemode + UI failure taxonomy + failure-report skeleton),sensitive-data(redaction),qa-structure(slug + failure-analysis path) </workflow_context>
<failure_analysis_contract>
The analysis artifact is tracked + downstream-fed — PUBLIC by default. USE SKILL sensitive-data: scan the rendered artifact BEFORE writing, fail-closed (no scan → no emit; logs/screenshots/page sources can carry tokens or PII). The failure classification is qa-knowledge's UI failure taxonomy (exactly one category per failure; Selector/Locator entries cite the captured page source). The artifact structure is qa-knowledge's failure-report template, UI variant — per failed test: ID F-N · Failure name · Error type · Root cause · Evidence label (Confirmed/Assumption/Unknown) · Evidence rationale · Recommendation; plus an Execution Summary and a Patterns section.
Example entry: **ID:** F-1 · **Failure:** login-redirect-missing · **Error type:** Selector/Locator · **Root cause:** login button selector #submitrenamed to#login-submit · **Evidence:** Confirmed · **Rationale:** report stack trace + captured page source both cited · **Recommendation:** update the selector in the LoginPage page object (Phase 8).
This is the phase contract, verified by <validation_checklist> independent of skill internals.
</failure_analysis_contract>
<phase_steps>
- Obtain or locate the test report
- Run read-only failure triage
- Review findings
- Update state </phase_steps>
<execute_analysis step="7.1" subagent="engineer" role="Test failure analyst">
- USE SKILL
qa-structureto resolve run paths/state. If the test report is not under a known path and not inagents/user-instructions/: ask user; WAIT until a report artifact is available or the user confirms none. - USE SKILL
sensitive-dataand run the fail-closed scan before reading or recording report values. Parse the sanitized execution summary first. With 0 failures, skip failure triage and continue directly to the zero-failures branch in step 7.3. - With one or more failures, USE SKILL
qa-knowledge(test_execution_triagemode) with the parent-supplied bindings: report path; taxonomy = the UI failure taxonomy; output contract =<failure_analysis_contract>; output path =plans/ui-aqa-<test-name>/failure-analysis.md; page-sources directory =plans/ui-aqa-<test-name>/page-sources/. The skill loads its own taxonomy + report skeleton at point of use. USE SKILLsensitive-datafor redaction and run its scan as the pre-emit gate before writing. - Honor the read-only scope (
<workflow_context>). - Post-analysis verification when failures exist: confirm
plans/ui-aqa-<test-name>/failure-analysis.mdexists with every<failure_analysis_contract>section. If missing/incomplete: re-run triage once with the same bindings; if still failing, stop Phase 7, recordPhase 7 blocked: failure-analysis.md not produced/incompleteinagents/TEMP/<FEATURE>/ui-aqa-state.md, and ask the user. </execute_analysis>
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.
- today First seen · 82 lines · 19 tokens per session scan A 2e7b4fbf071c
ui-aqa-flow-test-report-analysis is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 19 tokens to every session and 2,002 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.
Other commands, from other repositories
resolve-conflicts
Resolve merge conflicts on a GitHub PR by merging the base branch into the PR branch in an isolated git worktree, with JSON/markdown-aware conflict resolution.
rclone_completion
Output completion script for a given shell.
xpoz-best-practices
Reference docs for Xpoz query syntax, pagination, field selection, platform tools, and authentication. Usage: /xpoz-best-practices.
align
Verify spec-vs-spec alignment and brevity across the intent tree. This is NOT QA — QA checks code against a spec; alignment checks whether specs are consistent with their ancestors and internally tight against the Brevity Contract. The aligner runs three passes per walk.
deploy-check
Pre-flight verification before pushing to main. Reproduces the CI gates locally so the push doesn't fail in production.
validate-fix
Validate a proposed React fix with React-Sentinel assertions or replay checks.