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/buildermethods/design-os/design-tokensgit clone --depth 1 https://github.com/buildermethods/design-osWrote 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/buildermethods/design-os/design-tokens)<a href="https://agentmods.dev/commands/buildermethods/design-os/design-tokens"><img src="https://agentmods.dev/badge/commands/buildermethods/design-os/design-tokens.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 | $0.00000 | $0.01269 |
| Opus 5 | $0.00000 | $0.00634 |
| Sonnet 5 | $0.00000 | $0.00254 |
| Haiku 4.5 | $0.00000 | $0.00127 |
Grade A, and why
design-tokens 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 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.
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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Tokens
You are helping the user choose colors and typography for their product. These design tokens will be used consistently across all screen designs and the application shell.
Step 1: Check Prerequisites
First, verify that the product overview exists:
Read /product/product-overview.md to understand what the product is.
If it doesn't exist:
"Before defining your design system, you'll need to establish your product vision. Please run /product-vision first."
Stop here if the prerequisite is missing.
Step 2: Explain the Process
"Let's define the visual identity for [Product Name].
I'll help you choose:
- Colors — A primary accent, secondary accent, and neutral palette
- Typography — Fonts for headings, body text, and code
These will be applied consistently across all your screen designs and the application shell.
Do you have any existing brand colors or fonts in mind, or would you like suggestions?"
Wait for their response.
Step 3: Choose Colors
Help the user select from Tailwind's built-in color palette. Present options based on their product type:
"For colors, we'll pick from Tailwind's palette so they work seamlessly with your screen designs.
Primary color (main accent, buttons, links):
Common choices: blue, indigo, violet, emerald, teal, amber, rose, lime
Secondary color (complementary accent, tags, highlights): Should complement your primary — often a different hue or a neutral variation
Neutral color (backgrounds, text, borders):
Options: slate (cool gray), gray (pure gray), zinc (slightly warm), neutral, stone (warm gray)
Based on [Product Name], I'd suggest:
- Primary: [suggestion] — [why it fits]
- Secondary: [suggestion] — [why it complements]
- Neutral: [suggestion] — [why it works]
What feels right for your product?"
Use AskUserQuestion to gather their preferences if they're unsure:
- "What vibe are you going for? Professional, playful, modern, minimal?"
- "Any colors you definitely want to avoid?"
- "Light mode, dark mode, or both?"
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 · 167 lines · 0 tokens per session scan A 9cf883695f83
design-tokens is a command published in the GitHub repository buildermethods/design-os (1,847 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,269 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 2026-08-30.
Other commands, from other repositories
ui-flow-review
Review menus, HUD, navigation, and player flow from a UX perspective.
template-ui
Design a Sent template-builder interface.
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.
study
Runtime entry point for extracting design DNA from a live URL, screenshot, or reference site. Part of the Discovery lifecycle phase.
4-generate
Run Stage 4 of the design system skill generation pipeline: parallel skill file generation.
audit-ux
Whole-repo adversarial UX audit of the shipped user surfaces -> docs/audits/ux-audit- .md.