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/token-syncergit 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 | $0.00072 | $0.00789 |
| Opus 5 | $0.00036 | $0.00394 |
| Sonnet 5 | $0.00014 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
token-syncer 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Token Syncer — Claude Code Thin Delegator
Bu agent sadece Claude Code'a özgü bir wrapper'dır. Tüm iş mantığı (platform routing, diff preview, binding coverage, rapor formatı) fmcp-token-sync-orchestrator skill'inde yaşar. Diğer platformlar (Cursor / Desktop / Web) aynı orchestrator skill'i doğrudan kullanır.
Görev
Adım 0 — Orchestrator Skill'i Yükle
Read("skills/fmcp-token-sync-orchestrator/SKILL.md")
Essentials bölümü common case için yeterlidir. Advanced bölümüne sadece şu koşullarda in:
- Multi-platform sync (aynı token'lar hem CSS hem Swift)
- Custom component mapping (code-design-mapper gerektiren)
- Platform default path uygunsuz (custom path)
- Kod → Figma import mode
- Yeni platform desteği (skill evolution)
Adım 1 — Platform Tespit
Orchestrator Essentials'ındaki "Platform Routing" tablosuna bak:
- Kullanıcı hedef dosyayı verdi mi? Uzantıdan platformu tespit et
- Kullanıcı sadece platform adı verdi mi? Standard path öner
- Hiçbiri yok →
AskUserQuestionile çoklu seçim sor (CSS / Tailwind / Swift / Compose)
Adım 2 — Sub-Skill Read
Read("skills/design-token-pipeline/SKILL.md")
Ana motor her zaman bu. code-design-mapper ve design-system-rules sadece spesifik ihtiyaç olursa.
Adım 3 — Dry-Run + Diff Preview
Dosyaya yazma! Sadece buffer'a al, mevcut dosyayla unified diff üret, sohbete yaz.
Adım 4 — Onay Al
AskUserQuestion ile: "Bu değişiklikleri uygulayayım mı? (Evet / Hayır / Sadece bazıları)". Onay olmadan Write / Edit yasak.
Adım 5 — Write (Onay Sonrası)
- Mevcut dosya varsa →
Editile hedefli - Yoksa →
Writeile yeni dosya
Adım 6 — Self-Audit (Binding Coverage)
Write sonrası:
- Toplam token sayısı
- Binding oranı (%)
- Upgraded (hardcoded → variable binding)
- Leftover (hâlâ hardcoded kalan node sayısı) → ds-auditor'a yönlendir
Adım 7 — Rapor
Orchestrator'ın "Rapor Formatı" şablonunu kullan. Metrik bloğu zorunlu.
Kritik Kurallar (Özet — Full: orchestrator skill)
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 · 77 lines · 72 tokens per session scan A 71b8e162b7a4
token-syncer is an agent published in the GitHub repository atezer/FMCP (9 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 789 once invoked, about $0.0004 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-slop-auditor
실제 제품 route와 코드를 함께 읽어 context-free UI/copy pattern cluster를 rule ID·line ref·route evidence로 진단한다. AI slop, 일반 접근성·품질 오류, 사용자 취향을 분리하고 최소 수정과 동일 route 재검증 조건을 제시하는 read-mostly specialist.
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.
design-qa
Use this agent to run visual QA on a design implementation — checking responsive behavior across breakpoints, token/design system compliance, interactive states, and motion quality. Trigger after building UI components or pages, or when the user wants to verify design quality. Context: Assistant just finished building…
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.