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 agentmods add skills/uselayout/cli/layout-mdnpx skills add uselayout/cli --skill layout-mdgit clone --depth 1 https://github.com/uselayout/cliWhat 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 | $0.00053 | $0.01131 |
| Opus 5 | $0.00026 | $0.00566 |
| Sonnet 5 | $0.00011 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
layout-md 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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Layout design system skill
Use this skill whenever the repo contains a .layout/ directory (or an opened
layout.md file). It gives you the project's tokens, component patterns, and
rules so the code you generate matches the design system.
When to use
Invoke this skill for any task that produces UI, including:
- Creating new components (buttons, cards, forms, modals, pages)
- Editing existing components' styling
- Generating page layouts or sections
- Reviewing UI code for design-system compliance
- Answering questions like "what's our accent colour" or "how should I style X"
If the user opens a file in a folder with .layout/, assume this skill
applies even without explicit invocation.
What's available
Layout ships a local MCP server (@layoutdesign/context). If the user has
installed it via claude mcp add layout npx -- -y @layoutdesign/context serve,
the following MCP tools are available:
get_design_system— full layout.md contentget_design_section— one section (colours, typography, spacing, etc.)get_tokens— token values by categoryget_component— specific component's spec + codelist_components— every component with tokens usedcheck_compliance— validate generated code against design system rules
If the MCP server is not installed, read the files directly:
.layout/layout.md— full specification.layout/tokens.css— CSS custom properties.layout/tokens.json— W3C DTCG token format.layout/kit.json— manifest (name, version, tier)
Workflow for generating UI
Follow these steps in order:
1. Load context before writing code
Call get_design_system (or read .layout/layout.md) once per task. Pay
attention to:
- The "Quick Reference" section at the top: core tokens, primary component example, NEVER rules.
- The "Colour System" three tiers: primitive, semantic, component. Use semantic or component tokens in your code. Never reference primitive tokens directly.
- The "Components" section: the anatomy and states expected (default, hover, focus, active, disabled, loading, error).
- The "Anti-Patterns" section: rules you must not violate.
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.
- 2d ago First seen · 136 lines · 53 tokens per session scan A c691aa787912
layout-md is a skill published in the GitHub repository uselayout/cli (6 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 1,131 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…