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 MrBlushu/blushu-design-skills --skill check-the-stylegit clone --depth 1 https://github.com/MrBlushu/blushu-design-skillsWrote 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/mrblushu/blushu-design-skills/check-the-style)<a href="https://agentmods.dev/skills/mrblushu/blushu-design-skills/check-the-style"><img src="https://agentmods.dev/badge/skills/mrblushu/blushu-design-skills/check-the-style/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/mrblushu/blushu-design-skills/check-the-style"><img src="https://agentmods.dev/badge/skills/mrblushu/blushu-design-skills/check-the-style.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 | $0.00122 | $0.02175 |
| Opus 5 | $0.00061 | $0.01087 |
| Sonnet 5 | $0.00024 | $0.00435 |
| Haiku 4.5 | $0.00012 | $0.00217 |
Grade A, and why
check-the-style 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 12d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Check the Style
Set scope and mode
Require at least one concrete artifact: code, a runnable interface, URL, screenshot, recording, mockup, exported design, or pasted component. Inspect the project before asking for information already available on disk.
Use available tokens and themes, approved brand assets, target viewports, representative state and content fixtures, accessibility or localization constraints, visual baselines, and prior handoffs. Do not require every optional artifact for a local review; ask only for evidence whose absence would materially change the visual decision.
Infer the operating mode from the request:
- Review: inspect without modifying files; return prioritized findings and concrete fixes.
- Design direction: propose roles, tokens, variants, or visual decisions; do not apply them without authorization.
- Implementation: modify only the authorized code or design scope, preserve the existing stack and system, then verify the rendering.
- Focused refinement: address only the requested visual axis and load only its reference.
Treat “review,” “evaluate,” “explain,” and equivalent read-only phrasing as read-only. Treat “fix,” “refine,” “implement,” “apply,” and equivalent direct change requests as permission to edit within the named scope.
Keep product strategy, audience, outcomes, roadmap, interaction-pattern selection, navigation and flow design, full grid-system architecture, usability research, copywriting, semantic line composition, and complete accessibility audits outside scope. Refine the visual representation of already-decided patterns, states, content, and layout.
If the request is wholly outside visual design, do not solve it provisionally. State that the decision is outside this skill, name the appropriate workflow, and stop without proposing a product, interaction, navigation, flow, grid, copy, usability, or compliance solution. For a mixed request, continue only with an independent visual refinement; do not let a local assumption decide the blocked adjacent work.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 130 lines · 122 tokens per session scan A 1728f1bc3dd9
check-the-style is a skill published in the GitHub repository MrBlushu/blushu-design-skills (4 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 2,175 once invoked, about $0.0006 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 skills, from other repositories
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", or "vs best practices".
design
Use when designing or refreshing a web UI or landing page — visual concept, type/color/spacing/motion tokens, composition, rescuing a UI that reads AI-generic, or a graded design review. Brand-grounded and research-first; ships Tailwind v4 + Next.js 15 under WCAG 2.2 AA and Core Web Vitals budgets. NOT the words on…
webd
Web design workflow for landing pages, SaaS frontends, conversion-oriented pages, and non-generic UI. Use when building or improving a website, landing page, SaaS UI, hero section, pricing page, conversion funnel, shadcn/ui interface, or when the user invokes /webd or @webd.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
anti-ui-slop
Stop coding agents from shipping generic UI. Extend the product's design system, use UIZZE evidence only when useful, cover required states, and inspect the rendered result.