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 georgekhananaev/claude-skills-vault --skill semantic-codinggit clone --depth 1 https://github.com/georgekhananaev/claude-skills-vaultWrote 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/georgekhananaev/claude-skills-vault/semantic-coding)<a href="https://agentmods.dev/skills/georgekhananaev/claude-skills-vault/semantic-coding"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/semantic-coding/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/georgekhananaev/claude-skills-vault/semantic-coding"><img src="https://agentmods.dev/badge/skills/georgekhananaev/claude-skills-vault/semantic-coding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00056 | $0.04732 |
| Opus 5.5 | $0.00022 | $0.01893 |
| Sonnet 5.5 | $0.00011 | $0.00946 |
| Haiku 4.5 | $0.00006 | $0.00473 |
Grade A, and why
semantic-coding scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 407 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Coding
Scan files, replace hardcoded styles with semantic design tokens (colors, typography, spacing, sizing), edit files directly.
Refactored from
semantic-colors(color-only) into a comprehensive design system skill.
Usage
/semantic-coding [path]
DO NOT TOUCH (Non-Negotiable)
- Gradients:
from-*,via-*,to-*,bg-gradient-*,linear-gradient(),radial-gradient(),conic-gradient() - SVG defs:
<linearGradient>,<radialGradient>,<stop>,url(#...), anything inside<defs> - Glass morphism:
rgba(255,255,255,0.0x)overlays on gradient backgrounds - Decorative shadows:
boxShadowglow effects tied to gradient LED/orb effects - Animations:
@keyframes, animation timing values, transform values - Template literals:
`border-${color}-500`, dynamic class construction - Arbitrary values:
bg-[#hex],text-[14px],p-[20px](JIT bracket syntax) - Component props: Color/style values passed as non-className props (e.g.,
<Button color="red-500" />) - Token source files:
globals.css,tailwind.config.*,tokens.ts,theme.ts - Excluded dirs:
node_modules,.next,lib/generated,prisma/,dist/,__tests__/,*.test.*,*.spec.*
If a value is inside a protected context, skip and log ⚠ skipped (protected context).
Color Rules
Color Replacements
Note: Color-to-semantic mapping depends on your project's brand palette. The defaults below assume orange=brand, blue=info. If your brand uses blue/indigo/etc., map that family to
brandinstead and adjust accordingly.
| Hardcoded | Semantic |
|---|---|
text-red-*, text-rose-* |
text-error |
text-green-*, text-emerald-*, text-teal-* |
text-success |
text-yellow-*, text-amber-* |
text-warning |
text-blue-*, text-cyan-* |
text-info |
text-orange-* |
text-brand |
text-indigo-*, text-violet-*, text-purple-* |
text-primary |
text-pink-*, text-fuchsia-* |
text-accent |
text-gray-*, text-slate-*, text-zinc-*, text-stone-*, text-neutral-*, text-ink-* |
text-muted-foreground |
text-gray-900, text-slate-900, text-zinc-900 |
text-foreground |
text-white (on semantic bg) |
text-{bg-token}-foreground |
text-black |
text-foreground |
bg-red-*, bg-rose-* (shade ≥500) |
bg-error |
bg-red-*, bg-rose-* (shade <500) |
bg-error/10 |
bg-green-*, bg-emerald-*, bg-teal-* (shade ≥500) |
bg-success |
bg-green-*, bg-emerald-*, bg-teal-* (shade <500) |
bg-success/10 |
bg-yellow-*, bg-amber-* (shade ≥500) |
bg-warning |
bg-yellow-*, bg-amber-* (shade <500) |
bg-warning/10 |
bg-blue-*, bg-cyan-* (shade ≥500) |
bg-info |
bg-blue-*, bg-cyan-* (shade <500) |
bg-info/10 |
bg-orange-* |
bg-brand or bg-brand/10 |
bg-indigo-*, bg-violet-*, bg-purple-* |
bg-primary or bg-primary/10 |
bg-gray-*, bg-slate-*, bg-zinc-*, bg-stone-*, bg-neutral-*, bg-ink-* |
bg-muted |
bg-white (page-level) |
bg-background |
bg-white (inside card/panel) |
bg-card |
bg-black/50 (overlay) |
bg-overlay |
border-gray-*, border-slate-*, border-zinc-*, border-stone-*, border-neutral-*, border-ink-* |
border-border |
border-red-*, border-rose-* |
border-error |
border-green-*, border-emerald-*, border-teal-* |
border-success |
border-blue-*, border-cyan-* |
border-info |
border-yellow-*, border-amber-* |
border-warning |
border-orange-* |
border-brand |
border-indigo-*, border-violet-*, border-purple-* |
border-primary |
shadow-emerald-*, shadow-green-* |
shadow-success |
shadow-red-* |
shadow-error |
shadow-blue-* |
shadow-info |
ring-red-* |
ring-error |
ring-green-* |
ring-success |
ring-blue-* |
ring-info |
divide-gray-*, divide-slate-* |
divide-border |
placeholder-gray-* |
placeholder-muted-foreground |
What ships with it
1 file 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.
- 1mo ago First seen · 407 lines · 56 tokens per session scan A 560a6da77716
semantic-coding is a skill published in the GitHub repository georgekhananaev/claude-skills-vault (30 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 4,732 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 2026-09-03.
Other skills, from other repositories
html-to-bricks
Use when the user says 'convert this html to bricks' or 'paste html into bricks', or has a Webflow, Framer, CodePen, or old static export to bring into a Bricks site. Converts raw HTML and CSS into native Bricks elements, mapping colors, type, and spacing to design tokens, plus ACSS classes when installed.
frontend-design
A frontend design skill for building distinctive, production-ready web pages, components, and applications.
huashu-design
A design workflow for making high-fidelity HTML prototypes, slide decks, animations, visualizations, and design reviews. It requires three initial design directions before developing the selected one.
image-to-code
Turn a reference image, screenshot, or mockup into token-driven, accessible code. Infer the design system from the reference (palette, type scale, spacing, radius, layout archetype), map it to the 3-tier tokens, rebuild it, then verify with the kit's gates. Use when the user provides a design/screenshot and wants…
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…