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/sukirman1901/frontend-expert/polishgit clone --depth 1 https://github.com/sukirman1901/frontend-expertWrote 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/sukirman1901/frontend-expert/polish)<a href="https://agentmods.dev/commands/sukirman1901/frontend-expert/polish"><img src="https://agentmods.dev/badge/commands/sukirman1901/frontend-expert/polish.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 5.1 | $0.00013 | $0.00260 |
| Opus 5 | $0.00006 | $0.00130 |
| Sonnet 5 | $0.00003 | $0.00052 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
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.
What it actually says
Invoke the ui-quality-loop skill as the controller.
Agents per step
- Build/fix →
ui-developer - Test →
test-engineer - Audit →
design-reviewer
Skills
Lead with ui-quality-loop. Load domain skills as each step requires (frontend-judgment, design-tokens, ui-components, responsive-ui, motion + motion-families vocabulary, anti-ai-slop, ui-feel, accessibility, frontend-testing, audit chain).
Modes
/polish— full loop (default max 3 fix cycles)/polish --max N— override cap/polish --audit-only-fix— skip blank-canvas judgment; fix from audit
$ARGUMENTS selects modes.
What to do
- Follow
ui-quality-loopgates and cycle output template - Clear Critical/High only as blockers; leave Medium/Low unless asked
- Never infinite-loop — stop at cap with remaining list
- Do not fabricate audit metrics without tokens/screenshots
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 · 31 lines · 13 tokens per session scan A 92e6ad560f81
polish is a command published in the GitHub repository sukirman1901/frontend-expert (10 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 260 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 2026-08-31.
Other commands, from other repositories
sddesign
Full spec-driven pipeline — walks brief → tokens → shape (spec) → craft (build) → converge → ship in one guided run. Writes .ui-craft/spec.md. Run when starting a net-new surface from scratch.
seed-create-component
Command "seed-create-component" from daangn/seed-design, covering 컴포넌트 생성 흐름, 인자 and 필수 결과.
craft
One-shot build pipeline for a complete surface from an outcome recipe — inputs (or defaults) → composition → theme → build order → acceptance bar. Use when the user asks for a whole surface ("build me a dashboard", "I need a landing page") and expects a shippable result, not component-level help.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
spec-screenshot
Analyze website screenshots and generate detailed implementation specs.