#415415th of 455 in Skills, plugins and prompts
claude-to-im-skill
Skill that bridges Claude Code or Codex to Telegram, Discord, Feishu, QQ, WeChat
- Stars
- 2.9k
- License
- MIT
- Last commit
- Mar 2026
- Language
- TypeScript
2,244 on 22 Apr 20262,904 on 11 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
A Node.js background daemon, installed as a Claude Code or Codex skill, that forwards chat messages from IM bots to a coding agent session through the Claude Agent SDK or Codex SDK. Replies, tool-use prompts and permission requests are sent back to the chat, with Allow/Deny buttons on Telegram and Discord and text /perm commands elsewhere. State is kept in JSON files under ~/.claude-to-im.
Who it is for: Developers who want to drive Claude Code or Codex from a chat app
Strengths
- Covers five IM platforms, any combination enabled at once
- Tool calls need explicit approval from chat, with a 5-minute timeout that auto-denies
- Sessions persist across daemon restarts; tokens stored chmod 600 and redacted in logs
- Daemon opens no inbound network listeners; setup wizard validates tokens against platform APIs
Weaknesses
- Streaming preview only on Telegram and Discord
- QQ supports C2C private chat only, with no groups and no image replies
- WeChat is single-account with QR login and text-based permissions
- Needs a separately installed and authenticated Claude Code or Codex CLI
What it needs
- no GPU
- Needs Node.js >= 20, Claude Code CLI, Codex CLI, Telegram/Discord/Feishu/QQ/WeChat bot credentials
- Models: Claude (via Claude Agent SDK), Codex (via Codex SDK)
Also in Skills, plugins and prompts
See all 455| Rank | Project | Score |
|---|---|---|
| 1 | claude-memPersistent cross-session memory plugin for Claude Code and other coding agents | 97 out of 100 |
| 2 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 97 out of 100 |
| 3 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 96 out of 100 |
| #4 | rufloAgent harness adding swarms, memory and hooks to Claude Code and Codex | 96 out of 100 |
| #5 | cavemanShortens coding-agent replies and compresses tool output before the model reads it | 95 out of 100 |