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.
git clone --depth 1 https://github.com/memi-design/design-sandboxWrote 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/memi-design/design-sandbox/sandbox)<a href="https://agentmods.dev/commands/memi-design/design-sandbox/sandbox"><img src="https://agentmods.dev/badge/commands/memi-design/design-sandbox/sandbox.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 | $0.00033 | $0.00374 |
| Opus 5 | $0.00016 | $0.00187 |
| Sonnet 5 | $0.00007 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00037 |
Grade A, and why
sandbox 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.
What it actually says
You are running the design-sandbox pipeline. The user wants to explore a design idea — not ship a deliverable. Iterate freely; defaults can be loose.
The user's input is: $ARGUMENTS
(If a screenshot is attached above this command, treat it as the visual source of truth.)
Pipeline
-
Decode. Invoke the
screenshot-decodersubagent with the input and any attached image/URL. Wait for its structured spec. -
Confirm scope with the user. Echo the spec's
Briefline + theOpen questions. If there are blocking ambiguities, ask them now in one tightAskUserQuestioncall before moving on. If there are no blockers, proceed. -
Scaffold. Invoke the
component-scaffoldersubagent with the spec. It will run shadcnaddcommands and writesrc/app/sandbox/page.tsx. -
Verify it renders. Run
pnpm typecheck. If clean, tell the user to openhttp://localhost:3000/sandbox(and offer to startpnpm devin the background if not already running). -
Motion (optional). If the brief mentions motion, animation, transitions, "feels", "loop", "reveal", or similar — invoke
motion-directorfor one motion pass. Otherwise stop here and wait for the user.
Tone
Terse. One sentence between phases — what just happened and what's next. No commentary.
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 · 26 lines · 33 tokens per session scan A e888c8d82726
sandbox is a command published in the GitHub repository memi-design/design-sandbox (7 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 374 once invoked, about $0.0002 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 commands, from other repositories
refactor-ui
Apply tactical UI improvements using Refactoring UI principles.
style-guide
Generate comprehensive design system documentation including colors, typography, spacing, components, and usage guidelines. Outputs production-ready Tailwind/CSS configuration.
premium-landing
Generate premium $5k+ quality SaaS landing pages using the Define → Build → Review → Refine framework.
sheleg-design
Apply the SHELEG Design methodology (single-clock, layered, degrade-to-calm motion) to the current landing-page / hero / scroll-animation task — or its style packs to product UI (dashboards, admin, internal tools).
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
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.