What is memi CLAUDE.md?

A project instruction file for Claude Code working on Mémoire, an AI design tool that connects Figma designs, user research, and generated code. It includes the project's working rules, architecture, and widget system.

Use it when working on Mémoire's Figma workflow, widgets, design specifications, component generation, or related code.

It helps Claude Code follow the project's component structure, reuse existing connected code, and verify visual canvas changes.

memi CLAUDE.md — Instructions file for coding agents by memi-design: A project instruction file for Claude Code working on…

Install

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.

agentmods

npx agentmods add instructions/memi-design/memi/claude-md

Clone the repo

git clone --depth 1 https://github.com/memi-design/memi

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/memi-design/memi/claude-md.svg)](https://agentmods.dev/instructions/memi-design/memi/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/memi-design/memi/claude-md"><img src="https://agentmods.dev/badge/instructions/memi-design/memi/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,576 This file is loaded in full into every session.

When invoked 2,576 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02576	$0.02576
Opus 5	$0.01288	$0.01288
Sonnet 5	$0.00515	$0.00515
Haiku 4.5	$0.00258	$0.00258

Measured 5d ago against content hash 8509cf090f21, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

memi CLAUDE.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.

CLAUDE.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mémoire — Guidelines for Claude

Prime Directives

Operate as an autonomous superagent — read designs, drive canvas, generate specs and code without waiting for permission. Burn tokens for quality. (Why: Mémoire is built for hands-free operation; hesitation breaks the flow.)
Use Atomic Design exclusively — every component specifies a level: atom → molecule → organism → template → page. (Why: enforced in specs, codegen, and Figma structure.)
Self-heal after every canvas operation — CREATE → SCREENSHOT → ANALYZE → FIX → VERIFY (max 3 rounds). (Why: floating elements, wrong sizing, and raw hex values are the top defects.)
Check Code Connect before creating anything — get_code_connect_map first. Use mapped components when they exist. (Why: duplicate components are the #1 design system debt source.)
Load relevant skills before acting — skills in skills/ define how agents operate. Read the skill file that matches your task.

What is Mémoire

AI-native design intelligence engine. Bridges Figma, user research, and code generation into a spec-driven system. Auto-discovers and connects to the Figma plugin, generates shadcn/ui components from structured specs, and exposes on-canvas agent status widgets for task visibility.

Use the Figma Control Plane as an operator surface, not only as a bridge transport
Check Jobs first for sync, capture, inspect, and healer state
Use Selection for node IDs, styles, variants, layout facts, and quick actions
Use System for bridge state, ports, latency, and buffered change-stream visibility
Treat canvas agent widgets as task/status surfaces, not as a durable communication log
Use memi connect --json and memi doctor --json when an agent needs machine-readable widget and bridge health

Architecture

Directory	Purpose
`src/engine/`	Core orchestrator, project detection, registry, token-differ, sync, code-watcher, pipeline
`src/figma/`	Figma bridge (WebSocket auto-discovery on ports 9223-9232), tokens, stickies
`src/research/`	Research engine (Excel, web, stickies → insights)
`src/specs/`	Spec types (component, page, dataviz, design, ia) + Zod validation
`src/codegen/`	Code generation (shadcn mapper, dataviz, pages) → atomic folders
`src/notes/`	Mémoire Notes — downloadable skill packs (loader, resolver, installer)
`src/preview/`	Localhost preview gallery (HTML + API server + pipeline/sync/agent dashboards)
`src/agents/`	Agent orchestrator, multi-agent registry, task queue, agent bridge, agent workers
`src/mcp/`	MCP server (stdio transport) — 14 tools, 3 resources for Claude Code/Cursor
`src/tui/`	Terminal UI (Ink/React)
`src/commands/`	CLI commands (Commander.js)
`skills/`	Built-in skill definitions — ship with the npm package
`plugin/`	Figma plugin (auto-discovers Mémoire on ports 9223-9232)

Read the full file on GitHub · 154 lines

Changes

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 · 154 lines · 2,576 tokens per session scan A 8509cf090f21

Subscribe to this mod's changes

memi CLAUDE.md is an instructions file published in the GitHub repository memi-design/memi (40 stars, last pushed 2d ago), licensed MIT. It adds 2,576 tokens to every session, about $0.0129 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 2026-08-30.

Data and AI Planning cli design-tokens figma mcp mcp-server

memi CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Mémoire — Guidelines for Claude

Prime Directives

What is Mémoire

Widget V2 Operating Model

Architecture

What this file has done since we first saw it

Other instructions, from other repositories

python-sdk AGENTS.md

frontmcp AGENTS.md

brain-in-the-fish CLAUDE.md

Web-Algebra CLAUDE.md

quarry CLAUDE.md

cdc-health-mcp-server CLAUDE.md