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 anilcancakir/claude-code --skill design-md-writergit clone --depth 1 https://github.com/anilcancakir/claude-codeWrote 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/anilcancakir/claude-code/design-md-writer)<a href="https://agentmods.dev/skills/anilcancakir/claude-code/design-md-writer"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code/design-md-writer/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/anilcancakir/claude-code/design-md-writer"><img src="https://agentmods.dev/badge/skills/anilcancakir/claude-code/design-md-writer.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 | $0.00064 | $0.01854 |
| Opus 5.5 | $0.00026 | $0.00742 |
| Sonnet 5.5 | $0.00013 | $0.00371 |
| Haiku 4.5 | $0.00006 | $0.00185 |
Grade A, and why
design-md-writer 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 12d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DESIGN.md Writer
DESIGN.md tells an agent how an interface looks: exact token values (colours, type, radii, spacing, component styles) in YAML, and the reason for each in prose. The frontend-design skill builds from it, ac/design-director commits to it and critiques against it, and Google Stitch imports it as a design system. This skill writes it, updates it, or audits an existing one.
Scope: one file plus one pointer. It records a visual direction; it does not choose one. A palette or typeface comes from an existing theme, from the user, or from ac/design-director through the frontend-design skill. It does not edit UI code, README or CHANGELOG, and it does not write the architecture doc (the architecture-md-writer skill), the project's why and scope (the project-md-writer skill) or its commands and conventions (write AGENTS.md by hand). Report adjacent problems instead of fixing them.
The format is Google Labs' design.md, spec version alpha; the CLI @google/design.md is at 0.4.0 (checked 2026-11-01). Expect changes, and read references/visual-identity.md for the schema, section order and tooling before writing.
Where it sits
| Layer | File | Holds |
|---|---|---|
| Rules | AGENTS.md | commands, conventions, off-limits |
| How it is built | ARCHITECTURE.md | boundaries, invariants, flows |
| How it looks | DESIGN.md | tokens, component styles, visual rationale |
opencode loads AGENTS.md into every agent in full at session start, so DESIGN.md stays out of it and one pointer line with a UI trigger is the wiring.
Pick the mode
- No DESIGN.md exists: write.
- One exists and lints clean: update in place, keep its headings.
- One exists and agents ignore it, or its quality is unknown: audit first and report ranked findings; edit only when the user asked for the fix.
- The existing DESIGN.md describes architecture (no YAML tokens, sections like Components and Data flow): stop. Ask with the
questiontool whether togit mv DESIGN.md ARCHITECTURE.md(then thearchitecture-md-writerskill owns it) and write the visual file fresh. The move is the user's call.
What ships with it
3 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.
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.
- 12d ago Changed · -25 lines · +13 tokens per session 733a978c2459
- 14d ago Changed · +20 tokens per session ab8a32a42764
- 15d ago First seen · 131 lines · 31 tokens per session scan A 0708f73c1a03
design-md-writer is a skill published in the GitHub repository anilcancakir/claude-code (4 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 1,854 once invoked, about $0.0003 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 2026-10-31.
design-md-writer compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| design-md-writeranilcancakir/claude-code | Skill | 4 | 2d ago | MIT | A | 64 | Claude Code, Codex |
| researcherbitwize-music-studio/claude-ai-music-skills | Skill | 668 | today | CC0-1.0 | A | 38 | Claude Code |
| sheet-music-publisherbitwize-music-studio/claude-ai-music-skills | Skill | 668 | today | CC0-1.0 | A | 36 | Claude Code |
| validate-albumbitwize-music-studio/claude-ai-music-skills | Skill | 668 | today | CC0-1.0 | A | 33 | Claude Code |
| import-artbitwize-music-studio/claude-ai-music-skills | Skill | 668 | today | CC0-1.0 | A | 32 | Claude Code |
| plagiarism-checkerbitwize-music-studio/claude-ai-music-skills | Skill | 668 | today | CC0-1.0 | A | 35 | Claude Code |
| promote-ideabitwize-music-studio/claude-ai-music-skills | Skill | 668 | today | CC0-1.0 | A | 50 | Claude Code |