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 fubits1/svelte-skills --skill code-style-cssgit clone --depth 1 https://github.com/fubits1/svelte-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/fubits1/svelte-skills/code-style-css)<a href="https://agentmods.dev/skills/fubits1/svelte-skills/code-style-css"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/code-style-css/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/fubits1/svelte-skills/code-style-css"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/code-style-css.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 | $0.00037 | $0.00367 |
| Opus 5.5 | $0.00015 | $0.00147 |
| Sonnet 5.5 | $0.00007 | $0.00073 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
code-style-css 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.
What it actually says
CSS Code Style
- Only add layout/flow styles (flex, grid). No decorative styles unless asked.
- ALWAYS nest CSS and ALWAYS nest with
&. For the full nesting workflow (specificity analysis, block ordering, stylelint compliance), usefrontend:css-nesting.
Rules for styles you write
These rules apply to styles the task already calls for; they don't license decorative styles you weren't asked for.
- Never
transition: all; list the animated properties. Set the righttransform-origin; for SVG, transform a<g>wrapper withtransform-box: fill-box; transform-origin: center. - Lay out with flex or grid rather than JS measurement. Fix content that overflows instead of hiding scrollbars.
- Size text containers for short, average and very long content. A flex child that truncates text needs
min-width: 0; clamp multi-line text withline-clamp. - Full-bleed layouts pad with
env(safe-area-inset-*)so notches don't cover content. - Number columns and compared numbers use
font-variant-numeric: tabular-nums. - Group focus with
:focus-withinon compound controls. - Set
-webkit-tap-highlight-coloron purpose. During a drag, disable text selection (user-select: none;inertplacement:frontend:code-style). - Give native
<select>an explicitbackground-colorandcolor, or Windows dark mode renders it unreadable.
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 Changed · +13 lines c8cfcace5d39
- 2mo ago First seen · 11 lines · 37 tokens per session scan A 68536789b96c
code-style-css is a skill published in the GitHub repository fubits1/svelte-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 37 tokens to every session and 367 once invoked, about $0.0001 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.
code-style-css compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-style-cssfubits1/svelte-skills | Skill | 10 | 12d ago | MIT | A | 37 | Claude Code |
| anti-slop-designsickn33/agentic-awesome-skills | Skill | 49k | yesterday | MIT | A | 34 | Claude Code |
| chakra-ui-builderchakra-ui/chakra-ui | Skill | 41k | yesterday | MIT | A | 214 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 4d ago | MIT | A | 52 | Codex |
| open-design-setupcompozy/compozy | Skill | 2.8k | yesterday | MIT | A | 67 | Claude Code, Codex |
| edit-sitemicrosoft/power-platform-skills | Skill | 1.1k | yesterday | MIT | A | 104 | Claude Code |
| frontend-visual-qadaymade/claude-code-skills | Skill | 1.5k | yesterday | MIT | A | 125 | Claude Code, Codex |