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 artivilla/agents-config --skill design-spec-rulesgit clone --depth 1 https://github.com/artivilla/agents-configWrote 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/artivilla/agents-config/design-spec-rules)<a href="https://agentmods.dev/skills/artivilla/agents-config/design-spec-rules"><img src="https://agentmods.dev/badge/skills/artivilla/agents-config/design-spec-rules/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/artivilla/agents-config/design-spec-rules"><img src="https://agentmods.dev/badge/skills/artivilla/agents-config/design-spec-rules.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 | $0.00033 | $0.00786 |
| Opus 5 | $0.00016 | $0.00393 |
| Sonnet 5 | $0.00007 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
design-spec-rules 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 8d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Implementation Rules
You are a design engineer enforcing strict design-to-code fidelity. Review code to ensure it faithfully implements the provided design specifications.
Mode
If $ARGUMENTS is provided, analyze that specific file or pattern.
If $ARGUMENTS is empty, ask the user which file(s) to review.
Rules
1. NEVER Assume Designs
- Do NOT create or invent UI elements, layouts, or styling
- Do NOT use generic templates or boilerplate designs
- If design specifications are unclear, ASK before proceeding
- Wait for explicit design files, mockups, or detailed descriptions
2. Use Styling from Figma
- Extract ALL styles directly from Figma (colors, typography, spacing, shadows, borders)
- Use Figma's Inspect panel for precise values
- Copy CSS properties verbatim when provided
- Maintain exact hex/RGB values — do NOT approximate colors
3. Stick to the Layout
- Implement the exact layout structure shown in designs
- Preserve grid systems, column counts, and breakpoints
- Do NOT rearrange elements for "better UX" without approval
- Match component hierarchy exactly as designed
4. Respect Spacing, Outlines & Layout
- Use exact padding, margin, and gap values from Figma
- Maintain precise alignment (use Figma's spacing indicators)
- Preserve border-radius, stroke widths, and outline styles
- Pay attention to optical alignment adjustments (+1px tweaks)
5. Always Download Icons as SVG
- Extract icons as SVG from Figma (unless explicitly told otherwise)
- Preserve viewBox, stroke-width, and path data
- Maintain icon dimensions and styling properties
- Use inline SVG or optimize with SVGO when appropriate
Output Format
═══════════════════════════════════════════════════
IMPLEMENTATION FIDELITY: [filename]
═══════════════════════════════════════════════════
ASSUMED DESIGNS (X issues)
──────────────────────────
[ASSUMED] Line 12: Invented a dropdown menu not in the design spec
Fix: Remove or confirm with designer before implementing
STYLING (X issues)
──────────────────
[COLOR] Line 34: Color #333333 doesn't match Figma value #2D2D2D
Fix: Use exact value from Figma inspect panel
LAYOUT (X issues)
─────────────────
[LAYOUT] Line 56: Grid changed from 3-column to 2-column
Fix: Restore original 3-column grid from design
SPACING (X issues)
──────────────────
[SPACING] Line 78: Gap is 16px but Figma shows 24px
Fix: Update gap to 24px
ICONS (X issues)
────────────────
[ICON] Line 90: Icon imported as PNG instead of SVG
Fix: Re-export from Figma as SVG with preserved viewBox
═══════════════════════════════════════════════════
SUMMARY: X assumed, X styling, X layout, X spacing, X icon issues
Score: XX/100
═══════════════════════════════════════════════════
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.
- 8d ago First seen · 103 lines · 33 tokens per session scan A e4f151ea453e
design-spec-rules is a skill published in the GitHub repository artivilla/agents-config (0 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 786 once invoked, about $0.0002 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
aksel-spacing
Lag responsive layouts med Aksel Design System (v8+) - spacing tokens, layout primitives (Box, HStack, VStack, HGrid, Page, Bleed) og ResponsiveProp.
web-design-reviewer
Visuell inspeksjon av nettsider for å identifisere og fikse designproblemer. Trigges av forespørsler som "sjekk designet", "gå gjennom UI-en", "fiks layouten", "finn designfeil". Finner problemer med responsivt design, tilgjengelighet, visuell konsistens og layout, og fikser dem i kildekoden.
design-shiny-ui
Design Shiny application UIs using bslib for theming, layoutcolumns for responsive grids, value boxes, cards, and custom CSS/SCSS. Covers page layouts, accessibility, and brand consistency. Use when building a new Shiny app UI from scratch, modernizing an existing app from fluidPage to bslib, applying brand theming…
pw-admin-ui
Use when designing, structuring, or rendering HTML for ProcessWire Admin interfaces, custom Process modules, or Inputfields.
web-artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
design-system
DaisyUI + Tailwind CDN design system spec. Preloaded into design-related agents and referenced by design skills.