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 commands/sergei-aronsen/claude-code-toolkit/design-mdgit clone --depth 1 https://github.com/sergei-aronsen/claude-code-toolkitWrote 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/commands/sergei-aronsen/claude-code-toolkit/design-md)<a href="https://agentmods.dev/commands/sergei-aronsen/claude-code-toolkit/design-md"><img src="https://agentmods.dev/badge/commands/sergei-aronsen/claude-code-toolkit/design-md.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 | $0.00021 | $0.01311 |
| Opus 5 | $0.00010 | $0.00656 |
| Sonnet 5 | $0.00004 | $0.00262 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade B, and why
design-md scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
1. `cat "${TK_TOOLKIT_DIR:-$HOME/.claude/toolkit-src}/templates/design-md/INDEX.json"` (local clone, if present) Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
/design-md --offline # use the toolkit clone at $TOOLKIT_DIR instead of curl How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-md
Purpose
Install a single DESIGN.md at the project root (or .claude/DESIGN.md if the user prefers) so any coding agent — Claude Code, Cursor, Aider, Copilot CLI — has a structured design system (colors, typography, spacing, radii, motion) to follow when generating UI.
The brand-inspired DESIGN.md files are mirrored from the upstream catalog VoltAgent/awesome-design-md. Each file is a single self-contained Markdown document with YAML-frontmatter tokens. 71 brands available.
The mirror is pinned in manifest.json:vendor_pins.awesome-design-md (drift-tracked by /vendor-changelog).
Usage
/design-md # picker — list all brands, ask which one
/design-md <brand> # direct install (e.g. /design-md vercel)
/design-md --list # just print the 71 brand names
/design-md --offline # use the toolkit clone at $TOOLKIT_DIR instead of curl
What you should do
-
Pick a brand.
- If the user invoked
/design-md <brand>, use that argument. - Otherwise, fetch the brand list from the index — try in order:
cat "${TK_TOOLKIT_DIR:-$HOME/.claude/toolkit-src}/templates/design-md/INDEX.json"(local clone, if present)curl -fsSL https://raw.githubusercontent.com/sergei-aronsen/claude-code-toolkit/main/templates/design-md/INDEX.json
- Show the 71 brand names sorted. Ask which one. If the user names a brand that is not in the list, suggest the 3 closest matches by edit distance and ask again — do not guess.
- If the user invoked
-
Decide install path. Default:
<project-root>/DESIGN.md. If aDESIGN.mdalready exists at the project root, ask whether to (a) overwrite, (b) write to.claude/DESIGN.mdinstead, or (c) abort. -
Fetch the file. Two sources, in order:
- Local clone (preferred when available — offline-safe + version-pinned):
cp "${TK_TOOLKIT_DIR:-$HOME/.claude/toolkit-src}/templates/design-md/<brand>/DESIGN.md" <install-path> - Raw GitHub (curl from the toolkit mirror, not upstream — keeps the install on the vendor-pinned commit):
curl -fsSLA "$TK_USER_AGENT" "https://raw.githubusercontent.com/sergei-aronsen/claude-code-toolkit/main/templates/design-md/<brand>/DESIGN.md" -o <install-path>
- Local clone (preferred when available — offline-safe + version-pinned):
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.
- 4d ago First seen · 73 lines · 21 tokens per session scan B 7a8575302b9d
design-md is a command published in the GitHub repository sergei-aronsen/claude-code-toolkit (5 stars, last pushed 18d ago), licensed MIT. It adds 21 tokens to every session and 1,311 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
profile
Save, load, inspect, update, reset, or delete diagram-design client profiles.
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
ppt-image2-editable-rebuild
Rebuild image2 or imagegen reference slides as editable PowerPoint decks.
team-ui
Orchestrate UI/UX design team.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.