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 instructions/memi-design/design-sandbox/agents-mdgit 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/instructions/memi-design/design-sandbox/agents-md)<a href="https://agentmods.dev/instructions/memi-design/design-sandbox/agents-md"><img src="https://agentmods.dev/badge/instructions/memi-design/design-sandbox/agents-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 5.1 | $0.00306 | $0.00306 |
| Opus 5 | $0.00153 | $0.00153 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00031 | $0.00031 |
Grade A, and why
design-sandbox AGENTS.md 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 5d 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
This is NOT the Next.js you know
This version has breaking changes — APIs, conventions, and file structure may all differ from your training data. Read the relevant guide in node_modules/next/dist/docs/ before writing any code. Heed deprecation notices.
design2code.ground
General design sandbox. The full operating manual is .claude/CLAUDE.md.
Quick orientation
- Scaffold target:
src/app/sandbox/page.tsx - shadcn-first; theme tokens only; no hex literals
- Subagents:
screenshot-decoder→component-scaffolder→motion-director - Slash command:
/sandbox "<idea>"(or paste screenshot then/sandbox) - memi MCP available as
mcp__memoire__* - Proof gate:
pnpm verify - Pre-publish local proof:
MEMI_BIN=../memi/dist/index.js pnpm verify
Pointers for non-Claude tools
- Codex / Cursor / OpenCode: read this file +
.memoire/SOUL.md+.memoire/AGENTS.md - The memi CLI/MCP package is
@memi-design/[email protected]. - Use
memi mcp config --target genericto verify the no-Figma MCP command before configuring a client.
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.
- 5d ago First seen · 24 lines · 306 tokens per session scan A 6623dc405ca7
design-sandbox AGENTS.md is an instructions file published in the GitHub repository memi-design/design-sandbox (7 stars, last pushed 1mo ago), licensed MIT. It adds 306 tokens to every session, about $0.0015 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 instructions, from other repositories
get-shit-pretty CLAUDE.md
Claude Code instructions for jubscodes/get-shit-pretty, covering gsp — get shit pretty, must-always / must-never, git workflow, this repository and architecture.
design-skills AGENTS.md
AGENTS.md instructions for memi-design/design-skills, a project described as: Practical design judgment for AI coding agents: 94 governed skills for craft, research, generation, Figma, and Memi.
figma-console-mcp CLAUDE.md
Claude Code instructions for southleft/figma-console-mcp, covering figma console mcp, build & test, release process, known issues and architecture.
martin-loop AGENTS.md
AGENTS.md instructions for Keesan12/martin-loop, covering martinloop agent operating rules, repository authority, mandatory internal-first sequence, prohibited actions and required internal health proof.
super-ux CLAUDE.md
Claude Code instructions for ssheleg/super-ux, covering claude.md — super-ux, where the artifacts are, gates, adding a skill and adding a hard rule.
Agent-Skills AGENTS.md
AGENTS.md instructions for jscraik/Agent-Skills, covering agent-skills agent guide, root essentials, project-specific correction boundary and further guidance.