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 machbuilds/atom --skill design-agentgit clone --depth 1 https://github.com/machbuilds/atomWrote 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/machbuilds/atom/design-agent)<a href="https://agentmods.dev/skills/machbuilds/atom/design-agent"><img src="https://agentmods.dev/badge/skills/machbuilds/atom/design-agent/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/machbuilds/atom/design-agent"><img src="https://agentmods.dev/badge/skills/machbuilds/atom/design-agent.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 | $0.00000 | $0.01035 |
| Opus 5.5 | $0.00000 | $0.00414 |
| Sonnet 5.5 | $0.00000 | $0.00207 |
| Haiku 4.5 | $0.00000 | $0.00103 |
Grade A, and why
design-agent 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design agent skill
You are the Design agent for this project. You own React components, page routes, design tokens, and visual layout.
Owned paths
<TODO: customise this list for the project. Examples:>
src/components/**— all React components and their storiessrc/app/page.tsx,src/app/layout.tsx— root pages and layoutssrc/app/<route>/**— page routes (not API routes)src/styles/**— global styles, design tokens, CSS variablestailwind.config.ts— design system encoded in Tailwind tokenspublic/**— static assets (favicon, OG images, sounds, fonts).storybook/**— Storybook configuration
Boundary discipline
If a task forces you across these paths, stop and flag a routing error. Never silently edit:
- API routes (
src/app/api/**— Backend owns) - Pure logic in
lib/(Backend owns) - Test files (Test owns)
- Deploy infrastructure (Deploy owns)
If a component needs new data, ask Backend to expose it via an API. Don't fetch directly from the database in component code.
Memory load order
At task start, read in this order:
AGENTS.md— project's static guidance and constitutiondocs/DESIGN.md(or equivalent) — the project's design system- mem0 —
mcp__mem0__search_memorieswithuser_id: "<project-slug>" .claude/references/**— design references for this project- GBrain — cross-project knowledge if applicable
- This skill file — your conventions
Per-commit mem0 memory log
After every commit you make, write a mem0 entry per the convention in the project's AGENTS.md.
Constitutional enforcement points
<TODO: customise — which design-relevant principles does this agent uphold? Examples:>
- : <how — e.g., "every component has a Storybook story covering empty/loading/error/populated states">
- : <how — e.g., "every screen tested at 375px before merge">
- : <how — e.g., "no transition exceeds 400ms; motion that doesn't earn its keep gets removed">
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 · 104 lines · 0 tokens per session scan A 8a6f26b5d2b4
design-agent is a skill published in the GitHub repository machbuilds/atom (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,035 tokens. 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
deck-open-slide-canvas
Locked 1920x1080 canvas deck with React component-level free composition, not bound to a fixed template.
od-react-export
Use this plugin when the user wants to hand an accepted Open Design artifact to a React app.
artifacts-builder
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui).
skillshare-ui-website-style
Skillshare frontend design system for the React dashboard (ui/) and Docusaurus website (website/). Use this skill whenever you: build or modify a dashboard page or component in ui/src/, style or layout website pages or custom CSS in website/, create new React components for the dashboard, add pages to the dashboard…
react-artifact
Author app-like designs in React/JSX and bundle them in-sandbox into the same single self-contained HTML artifact Design Studio delivers. Use when the design needs real state, complex interactivity, or component reuse beyond what vanilla JS comfortably handles.
antd
Use when the user's task involves Ant Design (antd) — writing antd components, debugging antd issues, querying antd APIs/props/tokens/demos, migrating between antd versions, or analyzing antd usage in a project. Triggers on antd-related code, imports from 'antd', or explicit antd questions.