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-stylegit 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)<a href="https://agentmods.dev/skills/fubits1/svelte-skills/code-style"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/code-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/fubits1/svelte-skills/code-style"><img src="https://agentmods.dev/badge/skills/fubits1/svelte-skills/code-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 | $0.00048 | $0.01392 |
| Opus 5.5 | $0.00019 | $0.00557 |
| Sonnet 5.5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
code-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 11d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Style
REQUIRED SUB-SKILLS:
- When Svelte is involved (
.svelte,.svelte.ts,.svelte.js), invokesvelte-5:code-style-svelte. If thesvelte-5plugin isn't installed, stop and ask the user to install it. - When CSS is involved (CSS or SCSS files,
<style>blocks, inlinestyleattributes,style:directives), invokefrontend:code-style-css.
Brace Style
Single-line if without braces is OK only when the entire statement fits on one line:
// OK — fits on one line. But then we need an empty line after the statement, except there is another if, then we need an empty line after the last if.
if (x) doThing();
//OK
if (x) doThing();
if (y) doThingY();
if (z) doThingZ();
let x = 1
//NOT OK
if (x) doThing();
let x = 1
// NOT OK — body wraps to the next line, needs braces
if (x)
doThing();
// Correct
if (x) {
doThing();
}
HTML Data Attributes
Always use key-value syntax. Never use bare/boolean data attributes.
<!-- BAD -->
<div data-active></div>
<!-- GOOD -->
<div data-active="true"></div>
Markup and Locale
- A native
<button>activates on Enter and Space, an<a href>on Enter only. Use<button>for actions and<a href>for navigation to a real URL; only a non-semantic element with aroleneeds its own key handler. - Give inputs a meaningful
name, the matchingtype(email,tel,url,number) andinputmode, and turn off spellcheck on emails, codes and usernames (spellcheck="false"). - Give every field that collects information about the user its
autocompletetoken (name,email,tel,street-address,one-time-code), which WCAG 1.3.5 requires. Useautocomplete="off"only on a field that must never be autofilled. - Wrap a checkbox or radio and its text in one
<label>, so the whole row is a single hit target with no dead zone. - Keep a submit button enabled until the request starts, then show a spinner while it runs.
- Warn before the user leaves with unsaved changes:
beforeunloadon plain pages,beforeNavigateon SvelteKit (svelte-5:code-style-svelte). - Never disable zoom with
user-scalable=noormaximum-scale=1. Match<meta name="theme-color">to the page background. - During a drag, put
inerton the content that isn't a drop target, not on the dragged element (text selection:frontend:code-style-css). - Format dates, times, numbers and currency with
Intl.DateTimeFormatandIntl.NumberFormat. Detect the language fromAccept-Languageornavigator.languages, not the IP. Mark brand names, code and identifiers withtranslate="no".
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.
- 11d ago Changed · +6 lines 4798a45b1eb1
- 12d ago Changed · +12 lines · +9 tokens per session d2d64f042527
- 2mo ago First seen · 124 lines · 39 tokens per session scan A 435c4730d0ff
code-style is a skill published in the GitHub repository fubits1/svelte-skills (10 stars, last pushed 12d ago), licensed MIT. It adds 48 tokens to every session and 1,392 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.
code-style compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-stylefubits1/svelte-skills | Skill | 10 | 12d ago | MIT | A | 48 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |