What is fmcp-intent-router?

An entry-point workflow for Figma requests that determines what the user wants and gathers missing information before work begins. It can route the request to screen creation, library building, auditing, or another Figma task.

Use it at the beginning of any Figma-related request to clarify the goal, collect required inputs, summarize the proposed work, and obtain approval before changes are made.

It avoids starting the wrong Figma operation or making assumptions about missing details such as the device, design system, reference, or screen content.

fmcp-intent-router — Skill for Claude Code by atezer/FMCP

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.

Any agent

npx skills add atezer/FMCP --skill fmcp-intent-router

Clone the repo

git clone --depth 1 https://github.com/atezer/FMCP

Made for: Claude Code.

Or install figma-mcp-bridge, the plugin that ships this one along with the rest of its 29 skills, 10 commands, 3 agents, 1 MCP server.

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/skills/atezer/fmcp/fmcp-intent-router/github.svg)](https://agentmods.dev/skills/atezer/fmcp/fmcp-intent-router)

Your own site

<a href="https://agentmods.dev/skills/atezer/fmcp/fmcp-intent-router"><img src="https://agentmods.dev/badge/skills/atezer/fmcp/fmcp-intent-router/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/skills/atezer/fmcp/fmcp-intent-router"><img src="https://agentmods.dev/badge/skills/atezer/fmcp/fmcp-intent-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 153 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 10,013 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00153	$0.10013
Opus 5.5	$0.00061	$0.04005
Sonnet 5.5	$0.00031	$0.02003
Haiku 4.5	$0.00015	$0.01001

Measured 9d ago against content hash c0533066904c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fmcp-intent-router 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 9d 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.

skills/fmcp-intent-router/SKILL.md · 724 lines

How it starts

The opening of the file, as written. The whole thing — 724 lines — stays where its author put it; the contents beside it link to each section on GitHub.

F-MCP Intent Router — Universal Entry Gate

Neden Var?

F-MCP Bridge'in 20+ SKILL'i var. Her biri farklı bir iş yapar (ekran oluşturma, denetim, kütüphane inşası, vb.) ve her biri farklı input'lar ister. Claude kullanıcı "figma'da ekran yap" dediğinde:

Hangi SKILL lazım? (generate-figma-screen mi generate-figma-library mi?)
Hangi bilgiler eksik? (device? DS? benchmark? içerik bölümleri?)
Kullanıcı ne onay verdi?

Bu SKILL bu üç soruyu upstream çözer. Claude intent'i netleştirmeden hiçbir figma_execute, figma_create_frame, figma_clone_screen_to_device çalıştırmaz. "Hızlı ve doğru" kuralı: yanlış varsayım yapmaktansa 1 soru sormak her zaman daha hızlıdır.

Protokol (9 Adım — v1.9.1+)

Kullanıcı F-MCP ile ilgili herhangi bir talep yaptığında Claude bu 9 adımı SIRAYLA uygular. Hiçbir adım atlanmaz.

🚨 Adım 0 — DS GATE + BLANK FILE CHECK (v1.9.7+ MUTLAK İLK KAPI)

Herhangi bir intent analysis veya figma_ tool çağrısından ÖNCE:*

figma_get_status çağır — plugin bağlı mı, response'ta _bootstrap varsa direktifleri OKU (v1.9.7)
.claude/design-systems/active-ds.md dosyasını oku
Status: alanını kontrol et:
- ✅ Aktif → DS net, Blank File Sub-Check'e geç (madde 5)
- ❌ Henüz seçilmedi VEYA dosya yok → kullanıcıya DS sorusu sor (madde 4)
DS Sorusu (klasik): "Aktif bir design system belirlenmemiş. Hangi DS ile ilerlemek istersiniz? (örn. Material / Apple HIG / Tailwind UI / kendi library'niz)"
BLANK FILE SUB-CHECK (v1.9.7, ZORUNLU): figma_get_design_system_summary çağır.
- components === 0 && componentSets === 0 && variableCollections.length === 0 ise BOŞ DOSYA tespit edildi.
- _nextStep: "BLANK_FILE_DIALOG_REQUIRED" response'ta görünüyorsa, kullanıcıya 4 seçenek sun (AskUserQuestion tek call, 4 option):
```
Q: "Bu dosyada henüz Design System yok. Nasıl ilerleyelim?"
(a) Team library import — "Hangi library? Örn. Material 3, iOS HIG, Tailwind UI, veya kendi library'niz"
(b) Mini DS kur otomatik — figma_create_mini_ds tool'u çağrılır (12 color + 8 sizing + 3 text style + Button/Input/Card)
(c) Referans DS kopyala — "Material 3 template / iOS HIG template"
(d) DS'siz ilerle — linter tolerant mode, hardcoded değerler kabul (explicit acceptance)
```
- Seçim yapılmadan figma_execute createFrame YASAK. Claude ham createFrame denerse plugin _DESIGN_SYSTEM_VIOLATIONS_BLOCKING flag'i döndürür, retry zorunlu olur.
- Kullanıcı "(b)" derse Claude figma_create_mini_ds({ primaryColor, fontFamily, name }) tek tool çağrısı yapar, sonra ekran üretimine geçer.
- Kullanıcı "(a)" derse Claude figma_get_library_variables(libraryName) ile listeleme yapar, seçenek sunar.

Read the full file on GitHub · 724 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.

9d ago Changed c0533066904c
18d ago Changed · +1 lines 792ee934d063
1mo ago First seen · 723 lines · 153 tokens per session scan A cc75c502593c

Subscribe to this mod's changes

fmcp-intent-router is a skill published in the GitHub repository atezer/FMCP (10 stars, last pushed 9d ago), licensed MIT. It adds 153 tokens to every session and 10,013 once invoked, about $0.0006 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.

Building agents Design and UX ai claude cursor design-system design-tokens figma

accessibility-per-component

Audit one design system component's accessibility against WCAG 2.2 AA: keyboard, screen reader, contrast, focus, ARIA, target size. Trigger: a11y audit, is this accessible, WCAG check, screen reader support, keyboard navigation check. Not for page- or product-wide audits.

murphytrueman/design-system-ops · 68 tokens

figma-variable-audit

Audit Figma variable collections: tier mapping, naming, alias chains, modes, orphans; can fix in place with Figma Console MCP. Triggers: audit my Figma variables, review variable collections, Figma variable health. For token files in code use token-audit.

murphytrueman/design-system-ops · 63 tokens

theme-audit

Audit theme parity: tokens missing or unchanged per theme, component tokens bypassing semantics, contrast within each theme, resolver contexts, theme-switch regressions. Triggers: dark mode audit, theme coverage, brand variant parity. For general token structure use token-audit.

murphytrueman/design-system-ops · 57 tokens

token-audit

Audit how design tokens are defined: tiers, naming, alias chains, raw values, orphans, DTCG readiness. Triggers: audit my tokens, token architecture review, token health check. Not for code consuming tokens (token-compliance), theme parity (theme-audit) or Figma variables (figma-variable-audit).

murphytrueman/design-system-ops · 72 tokens

token-compliance

Find hardcoded colour, spacing and type values and wrong-tier token references in consuming code. Trigger: find hardcoded values, any hex in the code, are we using tokens correctly, token compliance. Do NOT use for token definitions — token-audit; token file format — schema-validator.

murphytrueman/design-system-ops · 62 tokens

ai-component-description

Write a six-section prose description (purpose, props, anti-patterns, composition, accessibility, examples) for a Figma component's description field so LLMs read it via MCP. Triggers: describe this component for AI, Figma MCP description. JSON metadata files: use metadata-schema-generator.

murphytrueman/design-system-ops · 65 tokens