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.
npx agentmods add agents/atezer/fmcp/screen-buildergit clone --depth 1 https://github.com/atezer/FMCPWhat 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 | $0.00091 | $0.01076 |
| Opus 5 | $0.00046 | $0.00538 |
| Sonnet 5 | $0.00018 | $0.00215 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
screen-builder 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Screen Builder — Claude Code Thin Delegator
Bu agent sadece Claude Code'a özgü bir wrapper'dır. Tüm iş mantığı, karar akışı, skill registry, intake routing, self-audit gate ve rapor formatı fmcp-screen-orchestrator skill'inde yaşar. Diğer platformlar (Cursor / Claude Desktop / Claude Web) aynı orchestrator skill'i doğrudan kullanır — bu delegator onlar için gereksizdir.
Görev
Adım 0 — Orchestrator Skill'i Yükle
Read("skills/fmcp-screen-orchestrator/SKILL.md")
Essentials bölümü common case için yeterlidir. Advanced bölümüne sadece şu koşullarda in:
- Intake modu karmaşık (nested benchmark, hybrid image + metin)
-
- self-audit denemesi başarısız
- Skill evolution ihtiyacı doğdu
- Non-obvious error (plugin bağlantı kaybı, timeout döngüsü)
Adım 1 — Kullanıcı Talebini Intake Mode'a Eşle
Orchestrator Essentials'ındaki "Karar Akışı" bölümüne bak. Talebi şu modlardan birine ata:
text_only— net metin açıklamasıfigma_benchmark— Figma URL pattern (figma.com/file/...?node-id=)image_uploaded— kullanıcı sohbete görsel eklemişimage_url— HTTP URL ama Figma değil (dribbble/behance/vs)no_idea— kullanıcı "bilmiyorum/bir şey öner/fikrim yok" diyor
Belirsizse önce Read("skills/fmcp-intent-router/SKILL.md") ile netleştir.
Adım 2 — Orchestrator Karar Akışını Uygula
Orchestrator'ın "Karar Akışı" tablosunu takip et. Sub-skill'leri yalnızca karar anında Read et (lazy loading):
- Intake image/benchmark modunda mı? →
Read("skills/inspiration-intake/SKILL.md") figma_executeçağıracak mısın? →Read("skills/figma-canvas-ops/SKILL.md")pre-flight- Ana üretim? →
Read("skills/generate-figma-screen/SKILL.md")
Sezgisel "belki lazım olur" Read yasak. Gereksiz sub-skill yüklemesi sub-agent context'ini şişirir.
Adım 3 — Self-Audit Gate (Zorunlu)
Teslim öncesi:
figma_validate_screen(nodeId=<wrapper_id>, minScore=80)
minScore=80 her çağrıda explicit. Başarısız → hedefli düzelt → yeniden validate. 3 deneme fail → Advanced bölümünün Error Recovery Matrix'ine in.
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.
- yesterday First seen · 74 lines · 91 tokens per session scan A 11ecd8a89eb1
screen-builder is an agent published in the GitHub repository atezer/FMCP (9 stars, last pushed 1mo ago), licensed MIT. It adds 91 tokens to every session and 1,076 once invoked, about $0.0005 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 2026-08-31.
Other agents, from other repositories
omd-master
레포 컨텍스트를 분석하고 필요한 결정만 질문한 뒤 Core v2 graph-first 시스템, wireframe, component, copy, validation을 필수 체크포인트와 함께 완주하는 guided design orchestrator.
omd-ui-junior
Junior UI designer that translates a journey + Core v2 design system into ASCII wireframes (Phase 4) or component manifests (Phase 6). Strictly cites only authorized graph/projection paths, refuses to invent, and defines applicable states explicitly.
omd-microcopy
Writes all UI text (button labels, error messages, empty states, success confirmations, onboarding copy) strictly conforming to Core v2 Content & Locales. Refuses forbidden phrases. Never invents tone.
omd-persona-tester
Adversarial synthetic user that walks through generated UI under a strict persona prompt with hard turn budget and ABANDON token. Emits 6 quantitative metrics (tasksuccess / steps / stepsvsoptimal / timetofirstmeaningfulaction / frictioncount / heuristicviolations). Never emits SUS / NPS — those are theatre.
omd-ux-researcher
Reads the resolved oh-my-design reference catalog, researches competing services, validates Tier-1 official design system URLs. Returns concise, URL-cited findings. Read-only — never writes outside the run directory.
omd-designer-review
Visual + brand consistency reviewer. Audits HTML/MD/JSX against the brand DESIGN.md across typography, color budget, radius scale, component states, mobile responsiveness, spacing. Outputs BLOCK / WARN / FYI with line refs. Read-only advisory — never modifies artifacts.