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 sauravvarma/garage --skill design-agentgit clone --depth 1 https://github.com/sauravvarma/garageWrote 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/sauravvarma/garage/design-agent)<a href="https://agentmods.dev/skills/sauravvarma/garage/design-agent"><img src="https://agentmods.dev/badge/skills/sauravvarma/garage/design-agent/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/sauravvarma/garage/design-agent"><img src="https://agentmods.dev/badge/skills/sauravvarma/garage/design-agent.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 | $0.00186 | $0.06732 |
| Opus 5 | $0.00093 | $0.03366 |
| Sonnet 5 | $0.00037 | $0.01346 |
| Haiku 4.5 | $0.00019 | $0.00673 |
Grade A, and why
design-agent 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 9d 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 — 505 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Agent
An isolated design subagent that generates and critiques production design variants. Produces Pencil frames and structured critique reports. Explicit invocation only — never auto-triggered.
This skill is Mode B. When not invoked, Claude Code operates in Mode A (the confirmed human-orchestrated chain: spec-first → implement → visual QA → sync gate → commit). Mode B wraps Mode A by adding a design phase before implementation.
When to use
- User explicitly says
/design-agent "design the contact page"or similar - User says
/design-agent "critique the home page frame"— critique-only mode - User says
/design-agent "design X — include a wild one"— with pushed variant - Never auto-trigger on design-related conversation
- Never suggest invoking this skill — wait for the user to invoke it
When NOT to use
- User asks to implement something (Mode A)
- User asks to fix a bug or adjust styling (Mode A)
- User asks to run visual QA (use /visual-qa instead)
- User wants to explore or discover a design direction (use /design-explore instead)
- User wants to challenge or revisit locked design decisions (use /design-explore Mode 5)
- Any task that doesn't start with explicit
/design-agentinvocation
Spec preflight
Before designing anything, verify the artifacts this skill depends on. Stop and present a checklist if anything required is missing — do not silently proceed with assumptions or invent values.
Required:
CLAUDE.md— project context, must contain a## Pencil design filesection with the absolute path to the.penfiledocs/BRIEF-AND-DIRECTION.md— tone, audience, goalsdocs/DESIGN-LANGUAGE.md— typography, color, layout philosophydocs/DESIGN-TOKENS.md— token valuesdocs/DESIGN-TAXONOMY.md— artifact index, frame naming conventiondocs/DESIGN-HEURISTICS.md— taste settings (created by/design-explore)docs/[FEATURE]-IDEAS.md— direction chosen + design variations for the feature being designed (created by/design-explore)
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.
- references/anti-patterns.md 6.6 KB
- references/critique-framework.md 7.1 KB
- references/layout-patterns.md 5.3 KB
- references/pencil-hygiene.md 9.3 KB
- references/pencil-rendering-quirks.md 4.6 KB
- references/taste-tuning.md 9.5 KB
- scripts/extract-icon-paths.js 7.5 KB runs code
- scripts/extract-mock-assets.py 6.2 KB runs code
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.
- 9d ago First seen · 505 lines · 186 tokens per session scan A a1a4c6716f18
design-agent is a skill published in the GitHub repository sauravvarma/garage (3 stars, last pushed yesterday), licensed MIT. It adds 186 tokens to every session and 6,732 once invoked, about $0.0009 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
extract-design
Extract the full design language from any website URL. Produces 8 output files including AI-optimized markdown, visual HTML preview, Tailwind config, React theme, shadcn/ui theme, Figma variables, W3C design tokens, and CSS variables. Also runs WCAG accessibility scoring. Use when user says 'extract design', 'get…
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
system-pitch
Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…
stakeholder-brief
Write a one-page stakeholder brief translating design system health or status into business language. Trigger when someone says: stakeholder update, exec brief, leadership summary, status report for leadership, system status for non-designers, write a brief for the business, or anything about communicating design…
token-audit
Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…
accessibility-per-component
Run an accessibility audit on a specific design system component. Trigger when someone says: accessibility check, a11y audit, WCAG compliance, is this accessible, check accessibility, does this meet WCAG, screen reader support, keyboard navigation check, or anything about auditing the accessibility of a specific…