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-exploregit 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-explore)<a href="https://agentmods.dev/skills/sauravvarma/garage/design-explore"><img src="https://agentmods.dev/badge/skills/sauravvarma/garage/design-explore.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 5.1 | $0.00175 | $0.05404 |
| Opus 5 | $0.00088 | $0.02702 |
| Sonnet 5 | $0.00035 | $0.01081 |
| Haiku 4.5 | $0.00017 | $0.00540 |
Grade A, and why
design-explore 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 7d 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Explore
A creative exploration agent that helps discover design directions, critique existing work, and challenge assumptions — even when specs exist. Where /design-agent executes within decided constraints, /design-explore helps figure out what those constraints should be, or whether they're still the right ones.
Primarily invoked explicitly via /design-explore. May also activate when the user's design intent is ambiguous and needs triage between exploration and production.
When to use
- User says
/design-explore "what should the contact page feel like?" - User says
/design-explore "I want something different but I can't articulate what" - User says
/design-explore "critique this screenshot" - User says
/design-explore "I'm not sure the design direction is right anymore" - User says
/design-explore "what if we went a completely different way?" - User is pre-spec, exploring aesthetic direction
- User has specs but wants to pressure-test or pivot them
When NOT to use
- User wants compliant production variants within a locked direction →
/design-agent - User wants to implement a design → Mode A
- User wants visual QA of implemented code →
/visual-qa
Self-contained dependencies
All knowledge is embedded in references/:
references/design-traditions.md— cross-domain inspiration catalog (10 traditions)references/exploration-techniques.md— divergent methods, sensory vocabulary, genre subversion (7 techniques)references/direction-critique.md— lightweight 6-question critique for exploratory workreferences/pencil-rendering-quirks.md— known Pencil MCP rendering quirks (fresh-insert paint failures in cloned sheets, +50px y-offset on certain frames) and the clone-and-modify workaround
Load references progressively based on mode (see each mode's "References needed" line). Do not load the design references all upfront — load what the mode requires. Exception: load pencil-rendering-quirks.md before any mode that writes to a .pen file (the loose-sketch generation in modes that produce Pencil output). Skipping it risks burning a session on invisible-widget debugging.
What ships with it
4 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.
- 7d ago First seen · 364 lines · 175 tokens per session scan A 052dbef1af9f
design-explore is a skill published in the GitHub repository sauravvarma/garage (3 stars, last pushed 1mo ago), licensed MIT. It adds 175 tokens to every session and 5,404 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…
ai-component-description
Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…
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…