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 skills add cenconq25/claude-code-app-studio --skill team-polishgit clone --depth 1 https://github.com/cenconq25/claude-code-app-studioWrote 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/skills/cenconq25/claude-code-app-studio/team-polish)<a href="https://agentmods.dev/skills/cenconq25/claude-code-app-studio/team-polish"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/team-polish/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/skills/cenconq25/claude-code-app-studio/team-polish"><img src="https://agentmods.dev/badge/skills/cenconq25/claude-code-app-studio/team-polish.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 | $0.00044 | $0.01736 |
| Opus 5 | $0.00022 | $0.00868 |
| Sonnet 5 | $0.00009 | $0.00347 |
| Haiku 4.5 | $0.00004 | $0.00174 |
Grade A, and why
team-polish 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Polish
The dedicated polish-cycle orchestrator. Once features are functionally done, this skill drives them to release quality through five disciplines in parallel: performance, accessibility, motion, QA, and copy.
Team Composition
- performance-analyst — frame budget, cold start, memory, network, battery, app size.
- accessibility-specialist — VoiceOver / TalkBack, dynamic type, contrast, reduced-motion, keyboard nav.
- animation-specialist — animation correctness, haptic pairing, reduced-motion fallbacks, easing fidelity.
- qa-tester — manual walkthrough on the device matrix, soak validation.
- content-designer — final copy pass, length on every device, empty/error/loading states.
Spawn each via Task. All five can run in parallel — their inputs are independent.
Phase 1: Resolve Polish Scope
Parse argument:
--feature=<name>-> the feature's screens and flows.--area=<name>-> a thematic area (e.g., "auth", "paywall", "settings").- No argument -> ask the user.
Read in parallel:
- The feature's PRD and design package.
- Existing
/perf-profile,/security-audit,/asset-auditartifacts for the feature area. - Any open S3/S4 bugs scoped to this feature.
Define the polish bar with the user:
- Performance budgets per metric.
- Accessibility level (AA minimum, AAA aspirational).
- Localization completeness.
- Visual fidelity tolerance ("pixel-perfect" vs "design-aligned").
Phase 2: Spawn All Five Reviewers in Parallel
performance-analyst
Prompt template:
Polish target: [feature/area]. Run
/perf-profilescoped to this area. Identify any metric over budget. For each, propose a fix with impact estimate and effort.
accessibility-specialist
Prompt template:
Polish target: [feature/area]. Walk every screen with VoiceOver and TalkBack. Test dynamic type at min, default, and largest accessibility sizes. Test color contrast. Test reduced motion. Test external keyboard navigation. List every gap with severity.
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.
- 6d ago First seen · 272 lines · 44 tokens per session scan A 6e8554446ddd
team-polish is a skill published in the GitHub repository cenconq25/claude-code-app-studio (40 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 1,736 once invoked, about $0.0002 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 skills, from other repositories
qa-test-planner
Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.
design-qa
Internal prototype QA helper. Use only after a Product Design prototype, URL-to-code build, or image-to-code build has a source visual target and a rendered implementation to compare before handoff. Do not use for broad UX critique, design critique, product audits, or flow reviews; route those user-facing requests to…
health
Runs a budget-aware agent-assisted engineering health audit for instruction/config drift, hooks/MCP, verifier surfaces, and AI maintainability. Use when users ask in any language to audit Claude, Codex, Pi, agent instructions, MCP or hooks, verifier coverage, or AI-maintainability drift. Not for debugging application…
hunt
Finds root cause before applying fixes for errors, crashes, regressions, failing tests, broken behavior, and screenshot-reported defects. Use when users report in any language errors, crashes, broken behavior, regressions, failing tests, screenshot evidence, or something that used to work and now fails. Not for code…
chrome-cdp
Drive a headless Chrome over the Chrome DevTools Protocol (CDP) for browser QA — navigate, click, fill forms, read the DOM/accessibility tree, screenshot, and assert. Use whenever a task requires loading a web page and interacting with it like a user. Chrome is launched by a bash step (recipe below); this skill…
ui-craft-checks
Use this comprehensive gate for formal review, QA, launch handoff, exact-fidelity inspection, high-risk complex UI, or when the fast gate exposes a deeper craft problem. Ordinary single-screen work uses ui-design-executor and its bundled validator without loading this full matrix. Pair standalone artifacts with…