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/_orchestrator-protocolgit 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 | $0.00000 | $0.02537 |
| Opus 5 | $0.00000 | $0.01269 |
| Sonnet 5 | $0.00000 | $0.00507 |
| Haiku 4.5 | $0.00000 | $0.00254 |
Grade A, and why
_orchestrator-protocol 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orkestratör Protokolü — Tüm Agentlar İçin Ortak Kurallar
Bu dosya FCM projesindeki tüm orkestratör agentların uyması zorunlu 8 maddelik protokolü tanımlar. Her agent (screen-builder, ds-auditor, token-syncer) görev başlangıcında ilk eylem olarak bu dosyayı Read ile yüklemek zorundadır. Her agent dosyasında bu 8 maddeden üretilmiş 10 satırlık kondense inline checklist ayrıca durur (fallback).
1. Skill Registry (Explicit)
Agent, yetkili olduğu skill listesini kendi dosyasında explicit ilan eder. Her skill satırı şu alanları içerir:
name— kanonik skill adıfile_path—skills/<name>/SKILL.md(tam yol)trigger— agent bu skill'i hangi koşulda çağırırwhen_to_use— iş amacı (kısa)
Sezgisel "skill adını tahmin et" YASAK. Registry'de olmayan bir skill'i kullanmak → madde 7 (Skill Evolution Protocol).
Skill "çağırma" tekniği (KRİTİK — Claude Code'da Skill tool yoktur):
1. Read("skills/<name>/SKILL.md") ← tüm dosyayı context'e yükle
2. SKILL.md içindeki required_inputs'u topla
3. SKILL.md'nin adım listesini sırayla uygula
4. Çıktıyı SKILL.md'nin belirttiği formatta üret
Agent skill'i iç context'ine yükleyip geçici olarak onun rolüne bürünür. generate-figma-screen gibi 1000+ satırlık skill'ler okunduğunda agent'ın turn bütçesinin bir kısmı tükenir — bu yüzden madde 3 (Cheap-First) kritik.
2. Intent Routing (Önce fmcp-intent-router)
Belirsiz istekte ilk iş: Read("skills/fmcp-intent-router/SKILL.md") ve skill'deki 8-adım protokolü uygula. State files şunlardan okunur:
.claude/design-systems/active-ds.md— aktif tasarım sistemi.claude/design-systems/last-intent.md— son kullanıcı niyeti (LRU 5).claude/design-systems/intent-history.md— geçmiş kararlar
v1.8.2 build-from-scratch kuralı (authoritative source: skills/fmcp-intent-router/SKILL.md:68-80): Kullanıcı "alternatif", "varyasyon", "farklı", "yeni", "tasarla", "redesign" derse → approach=build-from-scratch KİLİTLİDİR, figma_clone_screen_to_device tool'u ASLA önerilmez. Clone tool'u yalnızca cihaz göçü (iPhone 13 → iPhone 17, aynı DS, aynı layout) için kullanılır.
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.
- 2d ago First seen · 186 lines · 0 tokens per session scan A c7177e7a72c3
_orchestrator-protocol is an agent published in the GitHub repository atezer/FMCP (9 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,537 tokens. 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-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-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-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.