Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/CrowdLinker/Skillsnpx agentmods add skills/crowdlinker/skills/designmdme-cliWrote 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/crowdlinker/skills/designmdme-cli)<a href="https://agentmods.dev/skills/crowdlinker/skills/designmdme-cli"><img src="https://agentmods.dev/badge/skills/crowdlinker/skills/designmdme-cli/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/crowdlinker/skills/designmdme-cli"><img src="https://agentmods.dev/badge/skills/crowdlinker/skills/designmdme-cli.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 | $0.00123 | $0.02953 |
| Opus 5.5 | $0.00049 | $0.01181 |
| Sonnet 5.5 | $0.00025 | $0.00591 |
| Haiku 4.5 | $0.00012 | $0.00295 |
Grade A, and why
designmdme-cli 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 2mo 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 — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
designmdme CLI
designmdme turns any public website into a DESIGN.md — a structured Markdown
spec of that site's design system (color tokens, typography scale, spacing, border
radius, shadows/elevation, and component patterns). It can optionally also produce a
self-contained HTML preview that renders those tokens as live visual specimens.
The DESIGN.md is built to be fed to coding agents: when a user asks you to build or restyle a UI to match a real brand, generate the spec first, read it, then write code against its exact token values instead of guessing colors and fonts.
When to use this skill
Use it whenever the task depends on an accurate, real design system from a live site:
- "Build a landing page in the style of stripe.com" → generate
stripe.com, read the DESIGN.md, then implement using its actual hex values and font stack. - "Match our marketing site's design" / "make this look on-brand" → extract that URL.
- "What's linear.app's color palette / font?" → generate and read the relevant section.
- Setting up a new project's design tokens from an existing reference site.
If the user only wants a quick visual impression and no code, the HTML preview
(--html) is the shareable artifact. For everything code-related, the Markdown is the
source of truth.
Install
The binary is designmdme, published as @crowdlinker/designmdme.
# One-off (no install)
npx @crowdlinker/designmdme stripe.com
# Or install globally so the `designmdme` command is always available
npm install -g @crowdlinker/designmdme
Authentication (one-time, interactive)
The CLI is account-gated; generation requires a logged-in token. Auth uses a browser
device-code flow and stores a token at ~/.designmdme/auth.json (token + expiry only,
no other PII). Tokens default to a 30-day lifetime.
designmdme login # opens a browser, prints a fallback URL + code, then polls
designmdme whoami # prints the logged-in email + token expiry
designmdme logout # deletes ~/.designmdme/auth.json
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.
- 2mo ago First seen · 238 lines · 123 tokens per session scan A 2f2c23518e20
designmdme-cli is a skill published in the GitHub repository CrowdLinker/Skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 123 tokens to every session and 2,953 once invoked, about $0.0005 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 2026-08-31.
designmdme-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| designmdme-cliCrowdLinker/Skills | Skill | 5 | 3mo ago | MIT | A | 123 | Claude Code, Codex |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 4d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |