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 fpindej/netrock --skill polish-uigit clone --depth 1 https://github.com/fpindej/netrockWrote 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/fpindej/netrock/polish-ui)<a href="https://agentmods.dev/skills/fpindej/netrock/polish-ui"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/polish-ui/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/fpindej/netrock/polish-ui"><img src="https://agentmods.dev/badge/skills/fpindej/netrock/polish-ui.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 8 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium MCP Rug Pull · line 11 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 12 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 13 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 14 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00053 | $0.01023 |
| Opus 5.5 | $0.00021 | $0.00409 |
| Sonnet 5.5 | $0.00011 | $0.00205 |
| Haiku 4.5 | $0.00005 | $0.00102 |
Grade A, and why
polish-ui 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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish or build a frontend surface to a high design standard, then prove it in a real browser.
This skill composes user-level skills installed at ~/.claude/skills/: design-taste-frontend, image-to-code, web-design-guidelines, playwright-cli, and the aesthetic packs shadcn, clean, premium. If any are missing, install them first:
npx skills add leonxlnx/taste-skill --skill design-taste-frontend --skill image-to-code -g -a claude-code -y
npx skills add vercel-labs/agent-skills --skill web-design-guidelines -g -a claude-code -y
npx skills add microsoft/playwright-cli --skill playwright-cli -g -a claude-code -y
npx skills add bergside/awesome-design-skills --skill shadcn --skill clean --skill premium -g -a claude-code -y
Arguments
- Target: a route (
/settings), a component path, or an image/mockup file. If omitted, ask what surface to work on. - Style (optional):
shadcn(default - matches this app),clean, orpremium. The style pack informs direction only; the app's existing tokens and components always win. Unified UX is a hard rule - never make one page feel like a different product.
Steps
-
Set design direction: Invoke the
design-taste-frontendskill and the chosen style pack skill. Distill their guidance into a short brief scoped to the target: hierarchy, spacing rhythm, typography, restraint. Filter out anything that conflicts with project hard rules (shadcn-svelte components, existing tokens, logical CSS, 44px touch targets, no overflow). -
If the target is an image or mockup: Invoke the
image-to-codeskill for its analysis method (section-by-section, readable reference views, no cards-inside-cards). Translate the output into Svelte 5 terms - the implementation must use runes,interface Props+$props(), shadcn-svelte components, and feature folders. Ignore the skill's instructions about generating images with Codex tooling; analyze the provided image instead. -
Implement via delegation: Pass the distilled brief to
frontend-engineer(Delegation Rule applies - the orchestrator does not writesrc/code). Include the specific taste/style constraints in the agent prompt so the direction survives the handoff.
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 · 42 lines · 53 tokens per session scan A 5e61c57a8a1d
polish-ui is a skill published in the GitHub repository fpindej/netrock (234 stars, last pushed 2d ago), licensed MIT. It adds 53 tokens to every session and 1,023 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 2026-08-30.
Other skills, from other repositories
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
temps-design-system
Classify a console screen (list/record/form), build it on @temps-sdk/ds templates and the shared shadcn primitives in @temps-sdk/ui, and follow the console's status vocabulary and status colour rules. Use for any new or changed console UI in web/src, and when building or extending web/packages/ds itself.
shadcn-sveltekit-design
Use when building, redesigning, beautifying, or refactoring SvelteKit pages and reusable components with shadcn-svelte, Bits UI, or the shadcn-svelte MCP. Trigger on landing pages, dashboards, marketing sites, app shells, forms, navbars, tables, dialogs, charts, sidebars, auth screens, blocks, responsive layouts…
modern-css
Implement or debug CSS layouts, responsive styles, themes, and motion. Use when choosing native CSS features or replacing legacy styling with browser-compatible CSS; not for unrelated frontend logic.
cratis-components-accessibility
Apply the accessibility conventions Cratis Components 4 actually implements — dialog initial-focus discipline and the armed-Enter hazard, supplying every accessible name as a localizable prop or provider message, putting the accessible name on the focusable element rather than the wrapper, keeping decorative icons…
cratis-components-styling
Style and theme an application built on Cratis Components 4 — the three stylesheet entries an app must import, the --cratis- design-token seam, choosing between the baseline theme, a product theme and fully owned styling, dark mode, the typed pt parts and data-cratis-part selectors, the optional renderer adapters, and…