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 OneWave-AI/open-agent-stack --skill polish-passgit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/polish-pass)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/polish-pass"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/polish-pass/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/onewave-ai/open-agent-stack/polish-pass"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/polish-pass.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 | $0.00051 | $0.00571 |
| Opus 5.5 | $0.00020 | $0.00228 |
| Sonnet 5.5 | $0.00010 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
polish-pass 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 1mo 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish Pass
Everyone can tell. The centered-hero-with-gradient-text, the three-feature-cards-with-icons, the "Unlock the power of" copy -- AI-built apps share a look, and losing it is the difference between a demo and a product. This pass hunts the tells and replaces them with decisions.
Workflow
- The tells audit. Sweep design and copy for the fingerprints: symmetric three-card grids, gradient text on dark hero, purple anywhere, emoji as icons, identical border-radius-and-shadow on every element, "Unlock/Supercharge/Seamlessly" copy, feature names that describe categories not benefits, every section the same width and rhythm. List each with location.
- Break the symmetry. Editorial moves: vary section rhythm (one full-bleed, one narrow, one asymmetric), let one element be genuinely large, use whitespace as a feature, align to a real grid but break it once deliberately. The page should read like it was art-directed, not generated.
- Rewrite the words. Copy passes the read-aloud test: specific over sweeping ("invoices chase themselves" not "streamline your workflow"), numbers where they exist, the user's vocabulary, zero filler adjectives. Microcopy too -- buttons, empty states, and errors are where products feel human or robotic.
- Motion with intent. Replace scattered hover effects with a small motion system: one entrance treatment, one emphasis move, consistent durations and easings. Motion that communicates hierarchy, not motion because an animation library was installed. If the app has more than three or four distinct durations, stop and run
motion-system-- this is a systemic fix, not a per-element one.micro-interactionscovers the hover/press/focus set, andmotion-perfcovers it stuttering on a phone. - Detail sweep. Favicon and OG image real, focus states designed (not default blue), empty/loading/error states written, dark surfaces layered by elevation not one flat color, and typography checked at actual phone size.
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.
- 1mo ago First seen · 24 lines · 51 tokens per session scan A cb8a561eb630
polish-pass is a skill published in the GitHub repository OneWave-AI/open-agent-stack (5 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 571 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
sketch
Throwaway HTML mockups: 2-3 design variants to compare.
scrollcraft
Premium scroll-driven landing pages; scroll = timeline.
impeccable
Frontend design guidance, upstream-maintained (impeccable).
auteur
Design and build cinematic, award-level web pages.
taste
Mandatory preflight for web frontend visual design. If available, call readskill for bundled:taste before the first frontend create or edit tool call whenever creating or visually styling a human-viewed web page, component, app, dashboard, or interactive report. Do not load it for non-visual frontend logic or…