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/ai-dvps/comate/claude-mdgit clone --depth 1 https://github.com/ai-dvps/comateWrote 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/ai-dvps/comate/claude-md)<a href="https://agentmods.dev/instructions/ai-dvps/comate/claude-md"><img src="https://agentmods.dev/badge/instructions/ai-dvps/comate/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 | $0.02422 | $0.02422 |
| Opus 5 | $0.01211 | $0.01211 |
| Sonnet 5 | $0.00484 | $0.00484 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade A, and why
comate 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 4d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Comate — Claude Code Project Guide
Comate is a desktop AI workspace that wraps Claude Code in a native Electron app. It uses a hybrid architecture: a React 18 + Vite frontend, an Express.js sidecar server, and an Electron desktop shell.
Quick Commands
| Command | Purpose |
|---|---|
npm run dev:server |
Start the Express backend with hot reload |
npm run dev:client |
Start the Vite dev server (port 5173) |
npm run dev:electron |
Start the Electron desktop app (Vite dev client + shell) |
npm run lint |
Run ESLint on .ts/.tsx |
npm run typecheck |
Type-check client, server, and Electron sources |
npm test |
Run server, client, Electron, and build-script unit tests |
npm run check |
Run the complete lint, type-check, and unit-test suite |
npm run test:client |
Run jsdom-based component/hook tests |
npm run test:server |
Run node:test server tests (excludes src/server/vendor/) |
npm run test:browser |
Run Playwright browser tests |
npm run release |
Build sidecar + CDP gate + Electron production bundle (electron-builder) |
Do not run
npm run devalongsidenpm run dev:electron— both start Vite and will conflict on port 5173.
Architecture
┌─────────────────┐ WebSocket / HTTP ┌──────────────────┐
│ Electron shell │ ←──────────────────────→ │ Express server │
│ (electron/) │ │ (src/server/) │
└────────┬────────┘ └────────┬─────────┘
│ │
│ Vite dev client / bundled UI │ sidecar Node process
↓ ↓
┌─────────────────┐ ┌──────────────────┐
│ React UI │ │ SQLite, Claude │
│ (src/client/) │ │ SDK, file I/O │
└─────────────────┘ └──────────────────┘
- Frontend (
src/client/): React 18, Zustand stores, Tailwind CSS, Radix primitives,lucide-reacticons. - Backend (
src/server/): Express API routes, service layer, SQLite storage viabetter-sqlite3. - Desktop shell (
electron/): Electron main process + preload, sidecar Node binary lifecycle, native browser views (WebContentsView), tray, updater. - Plugins (
claude-code-plugin/): Built-in local plugin marketplace shipped with the app bundle. - WeCom CLI (
packages/wecom-cli/): Workspace-packaged oclif-style CLI for WeChat Work integration.
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.
- 4d ago First seen · 180 lines · 2,422 tokens per session scan A 6b3897b6b27e
comate CLAUDE.md is an instructions file published in the GitHub repository ai-dvps/comate (106 stars, last pushed 4d ago), licensed Apache-2.0. It adds 2,422 tokens to every session, about $0.0121 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 instructions, from other repositories
nextclaw AGENTS.md
AGENTS.md instructions for Peiiii/nextclaw, covering nextclaw ai 常驻内核, 产品愿景, 沟通与推进, 深思与目标模式 and 协作与 git 安全.
moonproxy-desktop AGENTS.md
Instructions for MoonProxyHQ/moonproxy-desktop, covering moonproxy, 功能, 技术栈, 目录结构 and 配置与数据存储.
code-by-wire CLAUDE.md
Instructions for luojiahai/code-by-wire, covering claude.md, development, website, architecture and code style.
markra AGENTS.md
AGENTS.md instructions for markrahq/markra, covering markra engineering guidelines, package management, tech stack, code organization and codemirror editor invariants.
Token-Dashboard CLAUDE.md
Instructions for Arylmera/Token-Dashboard, covering claude.md, project overview, status, architecture and data source.
ideate AGENTS.md
Instructions for paultyng/ideate, covering agents.md, build features as mcp tools first, ui second, when to add ui and pattern.