crewdesk CLAUDE.md

crewdesk CLAUDE.md is an instructions file for coding agents from mhmmdglc/crewdesk. It costs 1,108 tokens per session, scanned A, original, MIT.

Repository instructions for crewdesk, a small local dashboard that monitors Claude Code sessions. It runs with Node.js, has no build step, and can show either real local data or demo data.

In plain words
What is it for?
Running crewdesk, using its demo mode, checking JavaScript files, understanding its directories, and knowing which files handle the server, local Claude data, and browser interface.
Why use it?
They explain how the dashboard works and identify rules that prevent changes from breaking its data sources, security checks, or update behaviour.

Instructions file

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 instructions/mhmmdglc/crewdesk/claude-md
Clone the repo
git clone --depth 1 https://github.com/mhmmdglc/crewdesk

Wrote 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.

agentmods badge for crewdesk CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mhmmdglc/crewdesk/claude-md.svg)](https://agentmods.dev/instructions/mhmmdglc/crewdesk/claude-md)
Your own site
<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>
Per session 1,108 This file is loaded in full into every session.
When invoked 1,108 The same file — it is already loaded in full.
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 $0.01108 $0.01108
Opus 5 $0.00554 $0.00554
Sonnet 5 $0.00222 $0.00222
Haiku 4.5 $0.00111 $0.00111

Measured 3d ago against content hash 55ebd5715d2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 47 lines

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.mjshttp://127.0.0.1:4600 (gerçek ~/.claude okunur)
  • node bin/crewdesk.mjs demo --port 4610 → uydurma veri, gerçek veri okunmaz (--demo/-d de 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/.mjs dosyasına tek tek node --check. Otomatik test yok. Tek çağrıya birden çok dosya verme: node --check yalnızca 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

  1. ~/.claude'a asla yazma. Kendi durumumuz ~/.crewdesk/ altında.
  2. Sakla değil, türet. Oda, kuyruk, test turu — hepsi events.jsonl'den hesaplanır. Elle senkron tutulan alan ekleme.
  3. Ekran gerçeği söylesin. Koşmayan ajan çalışma odasına girmez. Gözlemlemediğin aktiviteyi çizme.
  4. Runtime bağımlılığı yok. dependencies boş kalacak.
  5. Dışarı istek yok. Telemetri, sürüm kontrolü, hiçbiri.
  6. Arayüzde kullanıcı/model üretimi her değer esc() ile kaçışlanır (task başlığı, ajan adı, owner, soru metni).

Read the full file on GitHub · 47 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. 3d ago First seen · 47 lines · 1,108 tokens per session scan A 55ebd5715d2e

Subscribe to this mod's changes

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.

Related

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/).

simonlin1212/Vibe-Research · 4,469 tokens

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.

Helicone/helicone · 791 tokens

worldmonitor AGENTS.md

AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.

koala73/worldmonitor · 2,492 tokens

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.

mckinsey/vizro · 332 tokens

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.

Prithvi-Web/TreeMap-Disk-Visualizer · 5,631 tokens

openclaw-dashboard CLAUDE.md

Instructions for mudrii/openclaw-dashboard, covering go development standards, project constraints, internal packages, environment and commands.

mudrii/openclaw-dashboard · 1,519 tokens