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 instructions/mhmmdglc/crewdesk/claude-mdgit clone --depth 1 https://github.com/mhmmdglc/crewdeskWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mhmmdglc/crewdesk/claude-md)<a href="https://agentmods.dev/instructions/mhmmdglc/crewdesk/claude-md"><img src="https://agentmods.dev/badge/instructions/mhmmdglc/crewdesk/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01108 | $0.01108 |
| Opus 5 | $0.00554 | $0.00554 |
| Sonnet 5 | $0.00222 | $0.00222 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
crewdesk CLAUDE.md 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.
How it starts
The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
crewdesk — Claude Notları
Claude Code oturumlarını izleyen lokal dashboard. Sıfır bağımlılık, Node 20+, derleme adımı yok. Repo: https://github.com/mhmmdglc/crewdesk (public, MIT).
Çalıştırma
node bin/crewdesk.mjs→ http://127.0.0.1:4600 (gerçek~/.claudeokunur)node bin/crewdesk.mjs demo --port 4610→ uydurma veri, gerçek veri okunmaz (--demo/-dde aynı şey). Demo verisi 30 sn'de bir yeniden yazılır, yoksa 90 sn sonra ekran sönüyor.npm run check→ tek doğrulama aracı: repodaki her.js/.mjsdosyasına tek teknode --check. Otomatik test yok. Tek çağrıya birden çok dosya verme:node --checkyalnızca ilkine bakar.
Sunucuyu yeniden başlatmadan src/ değişikliği etkili olmaz; public/ için sayfa yenilemek yeter.
Dizin
| Dosya | Sorumluluk |
|---|---|
bin/crewdesk.mjs |
CLI çözümleyici (bilinmeyen argüman = hata), demo alt komutu + periyodik tazeleme, bağlanma hatalarının açıklanması, loopback dışı bind uyarısı, eski veri dizini taşıma |
src/server.mjs |
HTTP + API, CSP, CSRF/Host doğrulama, statik sunum |
src/sources.mjs |
~/.claude'u okuyan tek dosya (proje, oturum, alt-ajan, token, ajan kadrosu) |
src/events.mjs |
Devir teslim kütüğü + oda türetme kuralları |
src/board.mjs |
Aşama/sahip overlay'i, anahtar doğrulama, atomik yazım |
public/app.js |
Arayüz mantığı, uyarılar |
public/office.js |
Canvas pixel ofis |
public/i18n.js |
6 dil (en varsayılan) |
demo/seed.mjs |
Uydurma ~/.claude ağacı; seed({ refresh: true }) zaman damgalarını tazeler, .crewdesk-demo işaretçisi olmayan dizini silmez |
Bozulmaması gereken kurallar
~/.claude'a asla yazma. Kendi durumumuz~/.crewdesk/altında.- Sakla değil, türet. Oda, kuyruk, test turu — hepsi
events.jsonl'den hesaplanır. Elle senkron tutulan alan ekleme. - Ekran gerçeği söylesin. Koşmayan ajan çalışma odasına girmez. Gözlemlemediğin aktiviteyi çizme.
- Runtime bağımlılığı yok.
dependenciesboş kalacak. - Dışarı istek yok. Telemetri, sürüm kontrolü, hiçbiri.
- Arayüzde kullanıcı/model üretimi her değer
esc()ile kaçışlanır (task başlığı, ajan adı, owner, soru metni).
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 · 47 lines · 1,108 tokens per session scan A 55ebd5715d2e
crewdesk CLAUDE.md is an instructions file published in the GitHub repository mhmmdglc/crewdesk (2 stars, last pushed 3d ago), licensed MIT. It adds 1,108 tokens to every session, about $0.0055 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 instructions, from other repositories
Vibe-Research AGENTS.md
Instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
helicone AGENTS.md
AGENTS.md instructions for Helicone/helicone, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
vizro copilot-instructions.md
Copilot instructions for mckinsey/vizro, covering github copilot instructions for vizro, pull requests from bots and automated tooling and everything else.
TreeMap-Disk-Visualizer AGENTS.md
Instructions for Prithvi-Web/TreeMap-Disk-Visualizer, covering treemap for agents, two ways in, the core workflow: scan → inspect → dry-run → act, the safety model (enforced server-side, not advisory) and mcp specifics.
openclaw-dashboard CLAUDE.md
Instructions for mudrii/openclaw-dashboard, covering go development standards, project constraints, internal packages, environment and commands.