[opensourcedex]

Claude-to-IM-skill is a free, open source ai interaction & interfaces project written in TypeScript and released under MIT. It has 2,880 GitHub stars, 316 forks and 100 open issues, and was last pushed 6 months ago. On this registry it ranks #82 of 135 tracked projects in AI Interaction & Interfaces, with 5 head-to-head comparisons available.

What is Claude-to-IM-skill?

Claude-to-IM-skill is a TypeScript skill that turns Telegram, Discord, Feishu/Lark, QQ, or WeChat into a chat front end for Claude Code and Codex, built for developers who want to drive an AI coding agent from a messaging app instead of a terminal.

What it is

Claude-to-IM-skill is an agent skill distributed for both Claude Code and Codex. It runs a background Node.js daemon that connects your IM bots to Claude Code or Codex sessions: messages arriving from chat are forwarded to the AI coding agent, and the responses come back to your chat, including tool use, permission requests, and streaming previews. The backend agent runtime is configurable through the CTI_RUNTIME environment variable, which accepts claude, codex, or auto. The project is written in TypeScript, licensed under MIT, and sits in the AI & Machine Learning / AI Interaction & Interfaces category.

The concrete problem it solves is keeping an interactive coding agent reachable when you are not sitting in front of the terminal that owns the session. It was extracted from CodePilot's IM bridge module for users who prefer a lightweight, CLI-only setup, so the specific thing it replaces for that job is the CodePilot desktop GUI itself. It lives in the agent-skill ecosystem for Claude Code and Codex, and it runs install-time tooling, guided token collection, and permission handling without requiring the user to write code.

Key capabilities

  • Bridges five IM platforms — Telegram, Discord, Feishu/Lark, QQ, and WeChat — and any combination of them can be enabled at once.
  • Switches the backing agent through CTI_RUNTIME, choosing between the Claude Agent SDK and the Codex SDK, or letting auto decide.
  • Gates tool calls behind explicit approval: inline buttons on Telegram and Discord, and /perm commands or quick 1/2/3 replies on Feishu, QQ, and WeChat.
  • Streams partial responses as the agent types them, on Telegram and Discord.
  • Persists sessions so conversations survive daemon restarts.
  • Protects secrets by storing tokens with chmod 600 permissions and auto-redacting them in all logs.
  • Provides an interactive setup wizard that collects tokens with step-by-step instructions, so the whole configuration path is /claude-to-im setup on Claude Code or claude-to-im setup on Codex.

Who uses it and how

  • Claude Code users install through npx skills add op7418/Claude-to-IM-skill and then run /claude-to-im setup; the skill appears in the / skill list of a new session.
  • Codex users clone the repository and run bash ~/code/Claude-to-IM-skill/scripts/install-codex.sh, which places the skill under ~/.codex/skills/claude-to-im, installs dependencies, and builds the daemon.
  • Developers working on the skill itself use the symlink flow into ~/.claude/skills/claude-to-im, or the Codex install script with --link, to iterate against a live checkout.
  • Teams already communicating on Feishu/Lark, QQ, or WeChat adopt it because those platforms approve tool calls by text command rather than by button, matching how those clients are used.
  • Users on Telegram or Discord get streaming previews as they work, which suits monitoring longer agent runs away from the desk.

Getting started

Install with npx skills add op7418/Claude-to-IM-skill and run /claude-to-im setup in Claude Code, or clone the repository and run bash ~/code/Claude-to-IM-skill/scripts/install-codex.sh and then claude-to-im setup in Codex. Either path requires Node.js 20 or newer and an installed, authenticated Claude Code CLI, a Codex CLI from npm install -g @openai/codex, or both.

How it compares

The facts name one adjacent tool: CodePilot, a full-featured desktop application with a visual chat interface, session management, a file tree preview, and permission controls. Claude-to-IM-skill is the lightweight CLI-only counterpart extracted from that project's IM bridge module, so the choice is between a GUI desktop experience and a headless daemon reached only through your existing chat apps.

When to use it — and when not to

A self-hoster must run and keep alive a Node.js daemon alongside an authenticated Claude Code or Codex CLI, and must create and configure bot credentials for each IM platform they enable; the project does not remove that operational surface. Anyone who wants a desktop window with a file tree and visual session management should pick CodePilot instead, and anyone not already using Claude Code or Codex has no runtime to bridge to. The repository is active but carries 100 open issues against 2,880 stars, and the README is published with a separate Chinese document, so parts of the operational guidance may be denser for readers who depend on the English text alone.

project readme (upstream, from github) — read inline

Claude-to-IM Skill

Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, Feishu/Lark, QQ, or WeChat.

中文文档

Want a desktop GUI instead? Check out CodePilot — a full-featured desktop app with visual chat interface, session management, file tree preview, permission controls, and more. This skill was extracted from CodePilot's IM bridge module for users who prefer a lightweight, CLI-only setup.

How It Works

This skill runs a background daemon that connects your IM bots to Claude Code or Codex sessions. Messages from IM are forwarded to the AI coding agent, and responses (including tool use, permission requests, streaming previews) are sent back to your chat.

You (Telegram/Discord/Feishu/QQ/WeChat)
  ↕ Bot API
Background Daemon (Node.js)
  ↕ Claude Agent SDK or Codex SDK (configurable via CTI_RUNTIME)
Claude Code / Codex → reads/writes your codebase

Features

  • Five IM platforms — Telegram, Discord, Feishu/Lark, QQ, WeChat — enable any combination
  • Interactive setup — guided wizard collects tokens with step-by-step instructions
  • Permission control — tool calls require explicit approval via inline buttons (Telegram/Discord) or text /perm commands / quick 1/2/3 replies (Feishu/QQ/WeChat)
  • Streaming preview — see Claude's response as it types (Telegram & Discord)
  • Session persistence — conversations survive daemon restarts
  • Secret protection — tokens stored with chmod 600, auto-redacted in all logs
  • Zero code required — install the skill and run /claude-to-im setup, or tell Codex claude-to-im setup

Prerequisites

  • Node.js >= 20
  • Claude Code CLI (for CTI_RUNTIME=claude or auto) — installed and authenticated (claude command available)
  • Codex CLI (for CTI_RUNTIME=codex or auto) — npm install -g @openai/codex. Auth: run codex auth login, or set OPENAI_API_KEY (optional, for API mode)

Installation

Choose the section that matches the AI agent product you actually use.

Claude Code

Recommended: npx skills
npx skills add op7418/Claude-to-IM-skill

After installation, tell Claude Code:

/claude-to-im setup

If you want WeChat specifically, you can also say:

帮我接微信
Alternative: clone directly into Claude Code skills
git clone https://github.com/op7418/Claude-to-IM-skill.git ~/.claude/skills/claude-to-im

Claude Code discovers it automatically.

Alternative: symlink for development
git clone https://github.com/op7418/Claude-to-IM-skill.git ~/code/Claude-to-IM-skill
mkdir -p ~/.claude/skills
ln -s ~/code/Claude-to-IM-skill ~/.claude/skills/claude-to-im

Codex

Recommended: use the Codex install script
git clone https://github.com/op7418/Claude-to-IM-skill.git ~/code/Claude-to-IM-skill
bash ~/code/Claude-to-IM-skill/scripts/install-codex.sh

For local development with a live checkout:

bash ~/code/Claude-to-IM-skill/scripts/install-codex.sh --link

The install script places the skill under ~/.codex/skills/claude-to-im, installs dependencies, and builds the daemon.

After installation, tell Codex:

claude-to-im setup

If you want WeChat specifically, you can also say:

帮我接微信桥接
Alternative: clone directly into Codex skills
git clone https://github.com/op7418/Claude-to-IM-skill.git ~/.codex/skills/claude-to-im
cd ~/.codex/skills/claude-to-im
npm install
npm run build

Verify installation

Claude Code: Start a new session and type / — you should see claude-to-im in the skill list. Or ask Claude: "What skills are available?"

Codex: Start a new session and say claude-to-im setup, start bridge, or 帮我接微信桥接.

Updating the Skill

Choose the update flow that matches both your AI agent product and your installation method.

Claude Code

If you installed with npx skills, re-run:

npx skills add op7418/Claude-to-IM-skill

If you installed via git clone or symlink:

cd ~/.claude/skills/claude-to-im
git pull
npm install
npm run build

Then tell Claude Code:

/claude-to-im doctor
/claude-to-im start

Codex

If you installed with the Codex install script in copy mode:

rm -rf ~/.codex/skills/claude-to-im
bash ~/code/Claude-to-IM-skill/scripts/install-codex.sh

If you installed with --link or cloned directly into the Codex skills directory:

cd ~/.codex/skills/claude-to-im
git pull
npm install
npm run build

Then tell Codex:

claude-to-im doctor
start bridge

Quick Start

1. Setup

Claude Code

/claude-to-im setup

Codex

claude-to-im setup

The wizard will guide you through:

  1. Choose channels — pick Telegram, Discord, Feishu, QQ, WeChat, or any combination
  2. Enter credentials — the wizard explains exactly where to get each token, which settings to enable, and what permissions to grant
  3. Set defaults — working directory, model, and mode
  4. Validate — tokens are verified against platform APIs immediately

2. Start

Claude Code

/claude-to-im start

Codex

start bridge

The daemon starts in the background. You can close the terminal — it keeps running.

3. Chat

Open your IM app and send a message to your bot. Claude Code / Codex will respond through the bridge.

When Claude needs to use a tool (edit a file, run a command), you'll see a permission prompt with Allow / Deny buttons right in the chat (Telegram/Discord), or a text /perm command prompt / quick 1/2/3 replies (Feishu/QQ/WeChat).

Commands

All commands are run inside Claude Code or Codex:

Claude Code Codex (natural language) Description
/claude-to-im setup "claude-to-im setup" / "配置" Interactive setup wizard
/claude-to-im start "start bridge" / "启动桥接" Start the bridge daemon
/claude-to-im stop "stop bridge" / "停止桥接" Stop the bridge daemon
/claude-to-im status "bridge status" / "状态" Show daemon status
/claude-to-im logs "查看日志" Show last 50 log lines
/claude-to-im logs 200 "logs 200" Show last 200 log lines
/claude-to-im reconfigure "reconfigure" / "修改配置" Update config interactively
/claude-to-im doctor "doctor" / "诊断" Diagnose issues

Platform Setup Guides

The setup wizard provides inline guidance for every step. Here's a summary:

Telegram

  1. Message @BotFather on Telegram → /newbot → follow prompts
  2. Copy the bot token (format: 123456789:AABbCc...)
  3. Recommended: /setprivacy → Disable (for group use)
  4. Find your User ID: message @userinfobot

Discord

  1. Go to Discord Developer Portal → New Application
  2. Bot tab → Reset Token → copy it
  3. Enable Message Content Intent under Privileged Gateway Intents
  4. OAuth2 → URL Generator → scope bot → permissions: Send Messages, Read Message History, View Channels → copy invite URL

Feishu / Lark

  1. Go to Feishu Open Platform (or Lark)
  2. Create Custom App → get App ID and App Secret
  3. Batch-add permissions: go to "Permissions & Scopes" → use batch configuration to add all required scopes (the setup wizard provides the exact JSON)
  4. Enable Bot feature under "Add Features"
  5. Events & Callbacks: select "Long Connection" as event dispatch method → add im.message.receive_v1 event
  6. Publish: go to "Version Management & Release" → create version → submit for review → approve in Admin Console
  7. Important: The bot will NOT work until the version is approved and published

QQ

QQ currently supports C2C private chat only. No group/channel support, no inline permission buttons, no streaming preview. Permissions use text /perm ... commands. Image inbound only (no image replies).

  1. Go to QQ Bot OpenClaw
  2. Create a QQ Bot or select an existing one → get App ID and App Secret (only two required fields)
  3. Configure sandbox access and scan QR code with QQ to add the bot
  4. CTI_QQ_ALLOWED_USERS takes user_openid values (not QQ numbers) — can be left empty initially
  5. Set CTI_QQ_IMAGE_ENABLED=false if the underlying provider doesn't support image input

WeChat / Weixin

WeChat currently uses QR login, single-account mode, text-based permissions, and no streaming preview.

  1. Run the local QR helper from your installed skill directory:
    • Claude Code default install: cd ~/.claude/skills/claude-to-im && npm run weixin:login
    • Codex default install: cd ~/.codex/skills/claude-to-im && npm run weixin:login
  2. The helper writes ~/.claude-to-im/runtime/weixin-login.html and tries to open it in your browser automatically
  3. Scan the QR code with

readme truncated — read the full docs on github

Frequently asked questions

Is Claude-to-IM-skill free to use?

Claude-to-IM-skill is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does Claude-to-IM-skill do?

Bridge Claude Code / Codex to IM platforms — chat with AI coding agents from Telegram, Discord, or Feishu/Lark.

What is Claude-to-IM-skill written in?

Claude-to-IM-skill is primarily written in TypeScript. Its source is publicly available at https://github.com/op7418/Claude-to-IM-skill, and it has 2,880 GitHub stars.