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-selector-implementationgit 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-selector-implementation)<a href="https://agentmods.dev/commands/griddynamics/rosetta/ui-aqa-flow-selector-implementation"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/ui-aqa-flow-selector-implementation.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 | $0.00018 | $0.01478 |
| Opus 5 | $0.00009 | $0.00739 |
| Sonnet 5 | $0.00004 | $0.00296 |
| Haiku 4.5 | $0.00002 | $0.00148 |
Grade A, and why
ui-aqa-flow-selector-implementation 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<ui_aqa_flow_selector_implementation>
<description_and_purpose> Add the selectors identified in Phase 4 to page objects, following project conventions and patterns. Writes page-object files only. </description_and_purpose>
<workflow_context>
- Phase 5 of 8 in
ui-aqa-flow - Input: the
## Selector ManagementPart A inventory from Phase 4 (in the test plan); page-object inventory from Phase 3 - Output: page objects extended/created with all required selectors; the Part B Implementation subsection recorded
- Prerequisite: Phases 1-4 complete
- Write boundary (single SSoT): writes ONLY page-object files (and the test plan's
## Selector Management→ Implementation subsection). No test files, fixtures, or frontend source. - Required skills:
qa-knowledge(implementation_modes— selector mode Part B),qa-structure(<test-name>paths + state shape) - Recommended skills:
coding(general repo hygiene),testing</workflow_context>
<skill_precedence>
If repository general hygiene and the selector-mode page-object rules disagree: follow the selector mode (per qa-knowledge implementation_modes) for selector locators, page-object accessor/getter/method conventions, and UI-specific patterns; follow coding for general repo hygiene (formatting, shared helpers, import order) where it does not override those selector decisions. Repo docs win on general-hygiene conflicts.
Resolved example (positive): repo standard prefers camelCase private helpers, but selector mode mandates getSubmitButton()-style accessors for elements touched by tests → use getSubmitButton() for page-object element access; keep camelCase for unrelated utilities (e.g. string builders) that are not selector accessors.
Anti-pattern (negative): renaming getSubmitButton() to submitBtn() "to match repo naming" for a mapped selector — wrong; that overrides the selector rules and must be reverted per the rule above.
</skill_precedence>
<part_a_inventory_gate>
The Phase 4 Part A inventory (the test plan's ## Selector Management section) MUST exist and be non-empty before any page-object write. If absent/empty: stop Phase 5, record Phase 5 blocked: Part A selector inventory missing — Phase 4 must run first in agents/TEMP/<FEATURE>/ui-aqa-state.md, and ask the user. Do NOT re-run Part A identification inside this phase — that is a phase-scope violation.
</part_a_inventory_gate>
<load_failure>
If qa-structure, qa-knowledge, testing, or coding cannot be loaded: retry once; if it still fails, stop, record the failed skill in agents/TEMP/<FEATURE>/ui-aqa-state.md, and ask the user. Do not author page objects from memory.
</load_failure>
<phase_steps>
- Execute selector implementation (step 5.1)
- Validate implementation (step 5.2)
- Update state (step 5.3) </phase_steps>
<execute_implementation step="5.1" subagent="engineer" role="Selector implementation specialist">
- USE SKILL
qa-structureto resolve run paths/state. Apply<part_a_inventory_gate>— stop if the Part A inventory is missing. - USE SKILL
codingto read the repository standards as authority for general hygiene before touching page objects; repo docs beat model defaults. - USE SKILL
qa-knowledge(implementation_modes— selector mode, Part B: implement) and USE SKILLtestingwith the parent-supplied bindings: Part A inventory source = the test plan's## Selector Managementsection; write boundary = page-object files only (<workflow_context>); output = the Implementation subsection. - Extend existing page objects (match existing patterns exactly: access modifiers, naming, formatting, helper-method shape) and create new ones as needed (use existing page objects as structural templates). Do not introduce new patterns from this workflow; resolve hygiene-vs-selector conflicts per
<skill_precedence>. - Fragile-selector gate: any selector Phase 4 flagged as fragile is NOT committed silently — replace it with a stable alternative agreed with the user, or surface it for explicit approval first. Record approval evidence in the Implementation subsection.
- Implementation report: Part B writes the
### Implementation (Part B only)subsection in the test plan's## Selector Managementsection (Page Objects Modified, Page Objects Created, Selectors Added, Methods Added, Fragile selectors implemented after approval). Step 5.3 echoes these intoagents/TEMP/<FEATURE>/ui-aqa-state.md. - Conditional doc-style match: add JSDoc/TSDoc on new selectors/methods ONLY if existing page objects in the same file/module already use it. Match the existing style; do not introduce doc comments to a module that lacks them. </execute_implementation>
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 · 88 lines · 18 tokens per session scan A 30fe8d3c509d
ui-aqa-flow-selector-implementation is a command published in the GitHub repository griddynamics/rosetta (342 stars, last pushed today), licensed Apache-2.0. It adds 18 tokens to every session and 1,478 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.
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.
rclone_mkdir
Make the path if it doesn't already exist.