Borrowing it
Nothing to install: this file belongs to im4codes/imcodes. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/im4codes/imcodes/master/CLAUDE.mdgit clone --depth 1 https://github.com/im4codes/imcodesWrote 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/im4codes/imcodes/claude-md)<a href="https://agentmods.dev/instructions/im4codes/imcodes/claude-md"><img src="https://agentmods.dev/badge/instructions/im4codes/imcodes/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/im4codes/imcodes/claude-md"><img src="https://agentmods.dev/badge/instructions/im4codes/imcodes/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02985 | $0.02985 |
| Opus 5.5 | $0.01194 | $0.01194 |
| Sonnet 5.5 | $0.00597 | $0.00597 |
| Haiku 4.5 | $0.00298 | $0.00298 |
Grade A, and why
imcodes 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 6d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
# Build & typecheck
npm run build # daemon (src/ → dist/)
npx tsc --noEmit # daemon typecheck only
npx tsc -p server/tsconfig.json --noEmit # server (stricter: noUnusedLocals, noImplicitReturns)
# Tests (vitest workspace)
npm test # all projects
npm run test:unit # daemon only (src/**/*.test.ts, test/**/*.test.ts, excludes e2e)
npm run test:server # server only (server/test/**/*.test.ts)
npm run test:web # web only (web/test/**/*.test.ts, jsdom environment)
npm run test:e2e # e2e only (test/e2e/**/*.test.ts, 30s timeout, requires tmux)
npx vitest run path/to/file.test.ts # single file
# Server (self-hosted backend)
cd server && npm run dev # run server via tsx
cd server && npm run migrate # apply PostgreSQL migrations
# Dev
npm run dev # run daemon via tsx
Architecture
IM.codes is a specialized instant messenger for AI coding agents — a three-tier system for remote terminal access, file browsing, multi-agent workflows, and session management:
You (browser / mobile app)
↓ WebSocket
Server (Node.js + Hono + PostgreSQL, self-hosted in server/)
↓ WebSocket
Daemon (Node.js CLI on user's machine, src/)
↓ tmux / ConPTY / transport
AI Agents (Claude Code / Codex / Gemini CLI / OpenClaw / Shell)
↔ imcodes send (agent-to-agent)
Daemon (src/)
Node.js process that manages AI agent sessions via tmux. Entry point: src/index.ts (commander CLI).
- Agent layer (
src/agent/): Two runtime backends — process agents run in tmux/ConPTY sessions, transport agents stream via network protocols.- Process drivers (
src/agent/drivers/):claude-code.ts,codex.ts,gemini.ts,opencode.ts,shell.ts— each implementsAgentDriver(build launch/resume commands, detect status via terminal patterns, capture output).tmux.tswraps tmux (Linux/macOS),conpty.tsprovides ConPTY (Windows). - Transport providers (
src/agent/providers/):qwen.ts(Qwen, LOCAL_SDK — spawns CLI process with stream-json output),openclaw.ts(OpenClaw, PERSISTENT — WebSocket to gateway). Each implementsTransportProvider—connect(),send(),onDelta(),onComplete(). Streaming is event-driven (no terminal scraping). - Agent types:
ProcessAgent = 'claude-code' | 'codex' | 'gemini' | 'opencode' | 'shell' | 'script',TransportAgent = 'openclaw' | 'qwen'. Defined insrc/agent/detect.ts. session-manager.tsmanages all sessions, auto-restart with loop prevention.provider-registry.tsmanages transport provider lifecycle.
- Process drivers (
- Transport relay (
src/daemon/transport-relay.ts): Converts transport provider callbacks (onDelta,onComplete,onError) to unified timeline events (assistant.text,session.state,tool.call). - Routing (
src/router/):message-router.tsroutes inbound messages to the correct session.command-parser.tshandles/bind,/status,/send, etc. - Server link (
src/daemon/server-link.ts): WebSocket client connecting to the server at/api/server/:id/ws. Sends{ type: 'auth', serverId, token }on open. Credentials stored in~/.imcodes/server.jsonafterimcodes bind. - Session store (
src/store/session-store.ts, SQLite layer insession-store-db.ts): SQLite (WAL) at~/.imcodes/sessions.sqlite, one row per session, debounced incremental writes in one transaction. The pre-SQLitesessions.jsonis imported once on first start and frozen assessions.json.migrated-to-sqlite; nothing reads it afterwards. Online snapshots:sessions.sqlite.bak.1-3.
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.
- 6d ago Changed · +68 tokens per session 60cf3eb3409c
- 1mo ago First seen · 107 lines · 2,917 tokens per session scan A 8a65a91dd248
imcodes CLAUDE.md is an instructions file published in the GitHub repository im4codes/imcodes (965 stars, last pushed today), licensed MIT. It adds 2,985 tokens to every session, about $0.0119 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.