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 commands/atezer/fmcp/ds-validategit 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 | $0.01807 |
| Opus 5 | $0.00000 | $0.00903 |
| Sonnet 5 | $0.00000 | $0.00361 |
| Haiku 4.5 | $0.00000 | $0.00181 |
Grade A, and why
ds-validate 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasarım Sistemi Kütüphane Doğrulaması
Kullanıcı "kütüphane doğrula", "DS'i validate et", "cache'i kontrol et", "DS uyumunu denetle" dediğinde bu komutu uygula. Eklenmiş DS'lerin repo template + user-local cache + state dosyalarının birbiriyle tutarlı olduğunu denetler.
Argüman
$ARGUMENTS
Argüman olabilir:
<library-id>→ sadece o kütüphaneyi doğrula- Boş → tüm kayıtlı kütüphaneleri sırayla doğrula
Adım 1: Hedef Belirleme
-
$ARGUMENTSboşsa:.claude/design-systems/altındaki tüm alt-dizinleri listele (README.md,active-ds.md,last-intent.md,intent-history.mdharicinde)- Tüm DS'leri sırayla doğrula
-
Kütüphane ID verilmişse → sadece
.claude/design-systems/<id>/için çalış
Adım 2: Her DS İçin Kontrol Listesi (9 kontrol)
Her DS için aşağıdaki 9 kontrolü sırayla yap ve rapor topla:
C1: Repo template dizini bütünlüğü
.claude/design-systems/<id>/var mı?- İçinde beklenen dosyalar var mı?
tokens.md(ZORUNLU — en azından başlık)components.md(ZORUNLU — en azından başlık)- Opsiyonel:
icons.md,mobile.md,assets.md,<ID>_CHEATSHEET.md
- Dosyalar boş değil mi? (her biri ≥5 satır)
C2: Repo template'de hassas key sızıntısı yok mu?
tokens.md+components.mdiçinde:- ❌ Hex değer (regex:
/#[0-9a-f]{6,8}\b/i) - ❌ Gerçek
componentKey/variableKey(regex:/key:\s*["']?[a-f0-9]{40}/i— 40 char alphanumeric) - ❌ Full file-key prefix (regex:
/[A-Z][a-z]*[0-9]{2,}[A-Za-z0-9]{15,}/— Figma file-key pattern)
- ❌ Hex değer (regex:
- Bulgular varsa WARNING olarak rapor et — bunlar user-local cache'e taşınmalıydı.
C3: User-local cache varlığı
~/.claude/data/fcm-ds/active.mddosyası var mı?- İçinde bu DS'in primary + secondary file-key'leri kayıtlı mı?
- Her file-key için
~/.claude/data/fcm-ds/<file-key>/dizini var mı?
C4: User-local cache bütünlüğü
Her user-local cache dizini için:
tokens.mdvar mı ve ≥1 variable entry içeriyor mu?components.mdvar mı ve ≥1 component entry içeriyor mu?_meta.mdvar mı ve parse edilebiliyor mu? (Sync Durumu, İstatistikler, Son sync tarihi)
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 · 157 lines · 0 tokens per session scan A d843a78ab928
ds-validate is a command 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 1,807 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 commands, from other repositories
full-diagnostic
Comprehensive design system health sweep.
describe-component
Generate an AI-optimised component description.
docs-coverage
Audit whether your documentation surface keeps pace with your components.
governance-review
Quarterly governance review package.
release-check
Pre-release validation pipeline for a component.
component-audit
Audit your component library inventory.