mimic-ai: Instructions file for Claude Code

CLAUDE.md

mimic-ai CLAUDE.md is an instructions file for Claude Code from miapre/mimic-ai. It costs 6,938 tokens per session, scanned A, original, MIT.

A project guide for Mimic AI, an MCP server that creates Figma designs from prompts, HTML, or descriptions using the target file’s existing components, design tokens, and layout rules. Figma is a collaborative tool for designing interfaces.

In plain words
What is it for?
Use it to create or update production-ready Figma screens with a project’s real components, text styles, tokens, and auto-layout.
Why use it?
It explains the required Figma token, library file key, and running plugin so the server can read the design system before building.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is miapre/mimic-ai's own configuration. It tells Claude Code how to work on mimic-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mimic-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to miapre/mimic-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/miapre/mimic-ai/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/miapre/mimic-ai

Made for: Claude Code.

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.

agentmods badge for mimic-ai CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/miapre/mimic-ai/claude-md.svg)](https://agentmods.dev/instructions/miapre/mimic-ai/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/miapre/mimic-ai/claude-md"><img src="https://agentmods.dev/badge/instructions/miapre/mimic-ai/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 6,938 This file is loaded in full into every session.
When invoked 6,938 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.06938 $0.06938
Opus 5 $0.03469 $0.03469
Sonnet 5 $0.01388 $0.01388
Haiku 4.5 $0.00694 $0.00694

Measured 7d ago against content hash 1aada08f6657, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

mimic-ai 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 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.

CLAUDE.md · 664 lines

How it starts

The opening of the file, as written. The whole thing — 664 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mimic AI

MCP server that builds production-ready Figma using the design system on the user's target file. Accepts prompts, HTML, or any description. Uses real components, tokens, and auto-layout. Learns from every build.

Prerequisites

  • FIGMA_TOKEN must be set in the MCP server config (or in ~/.mimic-ai.json as fallback). Without it, Mimic cannot read the library's components or text styles. Generate one in Figma: avatar (top-left) → Settings → Security → Personal access tokens → "Generate new token" (name: "Mimic AI", 90-day expiration). Five scopes required (all read-only): current_user:read, file_content:read, file_metadata:read, library_assets:read, library_content:read. Mimic validates the token on every build and guides users through setup or renewal if missing/expired.
  • Library file key is prompted once per library and cached permanently. The user copies it from the library file's URL: figma.com/design/<this-part>/...
  • Figma plugin must be running. In Figma desktop: Plugins > Development > Mimic AI > Run. The bridge connects automatically on first tool call.
  • fileKey is the alphanumeric string in the Figma URL: figma.com/design/<fileKey>/... — pass it to mimic_discover_ds.
  • Start every build with mimic_status. It returns the current phase and tells you what to do next.
  • Don't guess variable paths. Discovery populates the cache. Use figma_list_ds (kind: "variables" or "text_styles") to see what's available.

Component-First Principle

Target ~90% DS component usage, ~10% primitives with DS variables. Every build should maximize DS component coverage. Before creating ANY frame, check if the DS has a component for it. Section-level elements (header, footer, sidebar) and UI patterns (cards, metrics, tables, badges, buttons, inputs) should ALWAYS be DS components. Only use figma_create_frame for truly custom layouts that have no DS equivalent — and even then, bind every property to DS variables and text styles.

Read the full file on GitHub · 664 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.

  1. 7d ago First seen · 664 lines · 6,938 tokens per session scan A 1aada08f6657

Subscribe to this mod's changes

mimic-ai CLAUDE.md is an instructions file published in the GitHub repository miapre/mimic-ai (13 stars, last pushed 1mo ago), licensed MIT. It adds 6,938 tokens to every session, about $0.0347 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.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens