What is agentic-ui CLAUDE.md?

Design-system instructions for building user-interface components from Figma designs and their design tokens, which are named values for things like colors and spacing.

Use them to reproduce approved Figma components in production code with the required tokens, icons, states, source notes, and accessibility details.

They prevent the agent from guessing visual details, renaming tokens, using outside component libraries, or leaving interface states incomplete.

How alexgilev/agentic-ui configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to alexgilev/agentic-ui. 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/alexgilev/agentic-ui/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/alexgilev/agentic-ui

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/alexgilev/agentic-ui/claude-md/github.svg)](https://agentmods.dev/instructions/alexgilev/agentic-ui/claude-md)

Your own site

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

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/alexgilev/agentic-ui/claude-md"><img src="https://agentmods.dev/badge/instructions/alexgilev/agentic-ui/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,186 This file is loaded in full into every session.

When invoked 3,186 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.

Model	Per session	Once invoked
Fable 5.1	$0.03186	$0.03186
Opus 5.5	$0.01274	$0.01274
Sonnet 5.5	$0.00637	$0.00637
Haiku 4.5	$0.00319	$0.00319

Measured 2mo ago against content hash c97123ab04fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentic-ui 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 2mo 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 · 218 lines

How it starts

The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic UI — Design System Agent

You are a senior design engineer on a design system team. You think in tokens, not pixels. You ship components, not prototypes. Your output is auditable, composable, and production-grade.

Hard Rules

NEVER invent visual properties. Every color, spacing, radius, font, shadow, and border MUST trace to Figma or the token file. Missing value → ASK, never guess.
NEVER substitute an SVG. No emoji, unicode, or different SVG. Inaccessible icon → // TODO: Replace with actual SVG from Figma — [icon-name] with exact dimensions.
NEVER use external UI libraries. No MUI, Chakra, Shadcn, Radix. This is a custom design system.
NEVER hardcode hex values. All visual properties resolve to CSS custom properties.
NEVER create new design decisions. Reproduce what exists. No "I added a hover state for consistency."
Token names MUST match Figma exactly. AG / Button / Label / Regular → ag-button-label-regular. No renaming.
Every generated file includes: // Source: [Figma URL] · // Extracted: [date] · // Tokens: [list]
NEVER ship an interactive element without ALL states. Every <button>, <a>, <input>, clickable card, tab, toggle, or element with cursor: pointer MUST have:
- All Figma variant states implemented as CSS pseudo-classes (:hover, :focus-visible, :active, :disabled). Fetch the base component node from the "Component descriptions" section of the MCP response to see the full state/variant matrix. A snapshot of one instance only shows one state — never assume it's complete.
- Real click/state management. Interactive components MUST be 'use client' with actual state transitions. Static active props with no onClick handler is NOT interactive — it's a screenshot. Use controlled (activeIndex + onChange) or uncontrolled (defaultIndex + internal useState) patterns.
- An interactive component is NOT complete until every state in the Figma variant matrix has a corresponding CSS rule AND clicking/focusing/hovering produces the correct visual change in the browser.

Read the full file on GitHub · 218 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.

2mo ago First seen · 218 lines · 3,186 tokens per session scan A c97123ab04fd

Subscribe to this mod's changes

agentic-ui CLAUDE.md is an instructions file published in the GitHub repository alexgilev/agentic-ui (26 stars, last pushed 1mo ago), licensed MIT. It adds 3,186 tokens to every session, about $0.0127 per session on Opus 5.5. 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.

Design and UX Frontend

agentic-ui CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agentic-ui CLAUDE.mdalexgilev/agentic-ui	Instructions file	26	1mo ago	MIT	A	3,186	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

agentic-ui: Instructions file for Claude Code