ui-mcp: Instructions file for Claude Code

CLAUDE.md

ui-mcp CLAUDE.md is an instructions file for Claude Code from Forge-Space/ui-mcp. It costs 760 tokens per session, scanned A, original, MIT.

Project instructions for Forge-Space/ui-mcp, a TypeScript server that connects AI tools to user-interface and backend code generation services.

In plain words
What is it for?
Use them when building, testing, validating, or changing the ui-mcp project and its connection to the separate siza-gen package.
Why use it?
They give an agent the project’s commands, structure, dependencies, and architecture so it can work in the repository consistently.

Instructions file for Claude Code

Written for Claude Code: PostToolUse hook event. Also seen: mentions subagents.

This is Forge-Space/ui-mcp's own configuration. It tells Claude Code how to work on ui-mcp 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 ui-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Forge-Space/ui-mcp. 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/Forge-Space/ui-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Forge-Space/ui-mcp

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 ui-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/forge-space/ui-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/forge-space/ui-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/forge-space/ui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/forge-space/ui-mcp/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.

agentmods 80×15 button for ui-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/forge-space/ui-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/forge-space/ui-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 760 This file is loaded in full into every session.
When invoked 760 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 $0.00760 $0.00760
Opus 5.5 $0.00304 $0.00304
Sonnet 5.5 $0.00152 $0.00152
Haiku 4.5 $0.00076 $0.00076

Measured 2mo ago against content hash 1cfd7977ffdd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ui-mcp 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 · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Siza MCP

Quick Reference

NODE_OPTIONS=--experimental-vm-modules npm run build
NODE_OPTIONS=--experimental-vm-modules npm test
npm run registry:check          # validate server.json ↔ package.json
npm run validate:all            # lint + format + tsc + test + build

Project

  • Thin MCP protocol adapter for AI-powered UI/backend code generation
  • All AI/ML, generators, registry, feedback, and quality code lives in @forgespace/siza-gen
  • GitHub: Forge-Space/ui-mcp, default branch: main
  • npm: @forgespace/ui-mcp, binary: forgespace-ui-mcp
  • Bundle: ~403 KB (tools, services, resources only)

Architecture

@forgespace/ui-mcp (this repo)    @forgespace/siza-gen
├── src/index.ts (MCP server)     ├── ml/        (embeddings, quality, training)
├── tools/     (33 tool files)    ├── generators/ (react, vue, angular, svelte, html)
├── services/  (figma, analysis)  ├── registry/   (502 snippets, compositions, packs)
├── resources/ (MCP resources)    ├── feedback/   (self-learning, pattern promotion)
└── lib/       (browser, image)   └── quality/    (anti-generic rules, diversity)

Stack

  • TypeScript, Node 22, Jest ESM, tsup, pino
  • NODE_OPTIONS=--experimental-vm-modules required for Jest

Build/Test Pipeline

  • npm run build before npm test
  • Pre-push hook: lint → format:check → tsc → test → build
  • 45 test suites, 529 tests (tool-level + integration)
  • siza-gen has 343 additional tests for AI/registry internals

Distribution

  • server.json — MCP Registry metadata (io.github.forge-space/ui-mcp)
  • publish.yml — tag-driven: push v* → npm publish + MCP Registry + GitHub release
  • mcp-registry-status.yml — weekly tracking issue with npm/registry drift
  • registry:check — pre-publish validation (server.json ↔ package.json alignment)

What Stays Here

  • src/tools/ — 33 tool files (schema + handler glue)
  • src/services/ — Figma, analysis, generation, design services
  • src/resources/ — MCP resource providers
  • src/lib/ — browser-scraper, design-extractor, figma-client, image-analyzer, image-renderer, pattern-detector, prototype-builder, style-audit, tailwind-mapper, templates/
  • scripts/ — registry-check.mjs, mcp-registry-status.mjs

Read the full file on GitHub · 71 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. 2mo ago First seen · 71 lines · 760 tokens per session scan A 1cfd7977ffdd

Subscribe to this mod's changes

ui-mcp CLAUDE.md is an instructions file published in the GitHub repository Forge-Space/ui-mcp (2 stars, last pushed 6mo ago), licensed MIT. It adds 760 tokens to every session, about $0.0030 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 2026-08-31.

Related

ui-mcp CLAUDE.md compared with instructions from other repositories

ui-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ui-mcp CLAUDE.mdForge-Space/ui-mcpInstructions file26mo agoMITA760Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode