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/murphytrueman/design-system-ops/system-benchmarkgit clone --depth 1 https://github.com/murphytrueman/design-system-opsWhat 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 | $0.00009 | $0.00210 |
| Opus 5 | $0.00005 | $0.00105 |
| Sonnet 5 | $0.00002 | $0.00042 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
system-benchmark 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 3d 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.
What it actually says
Run the system-benchmark skill against the user's design system.
Load the system-benchmark skill from ${CLAUDE_PLUGIN_ROOT}/skills/system-benchmark/SKILL.md and follow its complete workflow.
If the user provided a file or directory path as an argument, use that as the system root: $ARGUMENTS
If no argument was provided, search the codebase for package.json, component directories, token files, and documentation to identify the system boundaries.
Before starting the benchmark, read the knowledge notes declared in the skill's frontmatter references: field, located in ${CLAUDE_PLUGIN_ROOT}/knowledge-notes/.
Produce the full benchmark report including: 12-dimension scores across 4 pillars, percentile positioning, pillar analysis, and improvement recommendations.
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.
- 3d ago First seen · 17 lines · 9 tokens per session scan A 49bd6b999967
system-benchmark is a command published in the GitHub repository murphytrueman/design-system-ops (174 stars, last pushed 11d ago), licensed MIT. It adds 9 tokens to every session and 210 once invoked, about $0.0000 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 2026-08-30.
Other commands, from other repositories
ds-add
Kullanıcı bir Figma linki ile yeni tasarım sistemi eklemek istediğinde bu komutu kullan. Bu komut yeni ekleme ve güncelleme arasındaki farkı otomatik tespit eder.
ds-sync
Mevcut bir tasarım sistemi kütüphanesini Figma'dan senkronize eder. Tam sync, kısmi sync ve resume (yarım kalanı devam ettirme) destekler.
ds-validate
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.
add-library
Kullanıcı "kütüphane ekle", "library ekle", "tasarım sistemi ekle", "design system ekle" dediğinde bu komutu uygula.
setup-rest-token
Kullanıcı "REST token kur", "REST token setup", "FIGMARESTTOKEN nasıl ayarlanır", "component discovery hızlandır" dediğinde bu komutu uygula.
install-library
Kullanıcı "kütüphane kur", "library kur", "library install", "kütüphane yükle", "kütüphane güncelle" dediğinde veya bir .md dosya yolu verip "bunu kur" dediğinde bu komutu uygula.