_orchestrator-protocol

A shared rulebook for the project's orchestrator agents, which are agents that coordinate other skills and steps. It defines how they declare, load, and use approved skills.

In plain words
What is it for?
Guiding agents such as screen builders, design-system auditors, and token synchronizers at the start of their work, including skill selection and execution order.
Why use it?
It gives agents a common process and prevents them from using unlisted skills or skipping required instructions.

Agent

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.

agentmods
npx agentmods add agents/atezer/fmcp/_orchestrator-protocol
Clone the repo
git clone --depth 1 https://github.com/atezer/FMCP
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,537 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.02537
Opus 5 $0.00000 $0.01269
Sonnet 5 $0.00000 $0.00507
Haiku 4.5 $0.00000 $0.00254

Measured 2d ago against content hash c7177e7a72c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

agents/_orchestrator-protocol.md · 186 lines

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 adı
  • file_pathskills/<name>/SKILL.md (tam yol)
  • trigger — agent bu skill'i hangi koşulda çağırır
  • when_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.

Read the full file on GitHub · 186 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. 2d ago First seen · 186 lines · 0 tokens per session scan A c7177e7a72c3

Subscribe to this mod's changes

_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.

Related

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.

kwakseongjae/oh-my-design · 49 tokens

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.

kwakseongjae/oh-my-design · 75 tokens

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.

kwakseongjae/oh-my-design · 57 tokens

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.

kwakseongjae/oh-my-design · 48 tokens

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.

kwakseongjae/oh-my-design · 48 tokens

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.

kwakseongjae/oh-my-design · 61 tokens