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/danecwalker/agentskills/build-design-systemnpx skills add danecwalker/agentskills --skill build-design-systemgit clone --depth 1 https://github.com/danecwalker/agentskillsWrote 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/danecwalker/agentskills/build-design-system)<a href="https://agentmods.dev/skills/danecwalker/agentskills/build-design-system"><img src="https://agentmods.dev/badge/skills/danecwalker/agentskills/build-design-system.svg" alt="Measured on agentmods" 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 | $0.00136 | $0.01509 |
| Opus 5 | $0.00068 | $0.00754 |
| Sonnet 5 | $0.00027 | $0.00302 |
| Haiku 4.5 | $0.00014 | $0.00151 |
Grade A, and why
build-design-system 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 3d 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.
Build Design System
Turn design evidence into a maintainable implementation system: foundations, tokens, reusable components, composed patterns, documentation, tests, and migration rules. Preserve the target framework and product behavior.
Apply these principles
- Treat user instructions and repository conventions as authoritative. Treat
DESIGN.mdas the design contract when present, but surface conflicts with verified production behavior instead of silently choosing one. - Extract every stable, reusable visual or behavioral contract that improves consistency. Keep one-off markup and business-specific workflows local.
- Prefer semantic HTML and platform behavior before custom roles or interaction code.
- Separate foundations, primitives, reusable components, product patterns, feature UI, and pages. Do not publish all of them from one package.
- Express repeated design decisions through semantic tokens. Avoid tokenizing accidental one-off values.
- Design small public APIs around meaning, composition, and explicit states. Avoid boolean-prop explosions and universal “do everything” components.
- Keep routing, data fetching, permissions, analytics policy, and business state outside foundational design-system components.
- Support all relevant states: default, hover, focus-visible, active, disabled, loading, empty, error, selected, open, responsive, and themed states as applicable.
- Make accessibility part of each component contract, not a final audit.
- Reuse the repository's existing accessible primitives, styling approach, test stack, and package tooling when sound. Do not introduce a parallel stack without a demonstrated need.
- Preserve visual assets, source code, and brand material only when the user is authorized to reuse them. Derive patterns from public references without copying proprietary implementation code.
Follow the workflow
1. Establish the source of truth
Identify whether the input is:
- a
DESIGN.mdand linked assets; - an existing project or component library;
- screenshots or design-tool exports;
- an authorized live website;
- or a combination.
What ships with it
8 files 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.
- agents/openai.yaml 255 B
- references/component-engineering.md 8.3 KB
- references/framework-adapters.md 6.3 KB
- references/public-sources.md 4.2 KB
- references/source-audit.md 7.4 KB
- references/system-structure.md 7.2 KB
- references/testing-and-accessibility.md 6.5 KB
- references/tokens-and-theming.md 7.1 KB
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.
- 3d ago First seen · 142 lines · 136 tokens per session scan A dcf1a98becc1
build-design-system is a skill published in the GitHub repository danecwalker/agentskills (2 stars, last pushed 9d ago), licensed MIT. It adds 136 tokens to every session and 1,509 once invoked, about $0.0007 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…