What is feishu-claude-bridge CLAUDE.md?

A setup guide for Feishu Claude Bridge, a Node.js service that connects Feishu or Lark chat to the Claude Code command-line tool. It covers prerequisites, building the service, and environment settings such as the app credentials and working directory.

Use it when installing, building, configuring, or running the bridge, including setting chat permissions, default coding modes, and the project directory.

It turns the project from source code into a configured chat bot and identifies the external accounts and tools it needs before it can run.

How PI-33/feishu-claude-bridge configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to PI-33/feishu-claude-bridge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PI-33/feishu-claude-bridge/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/PI-33/feishu-claude-bridge

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/pi-33/feishu-claude-bridge/claude-md/github.svg)](https://agentmods.dev/instructions/pi-33/feishu-claude-bridge/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pi-33/feishu-claude-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/pi-33/feishu-claude-bridge/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pi-33/feishu-claude-bridge/claude-md"><img src="https://agentmods.dev/badge/instructions/pi-33/feishu-claude-bridge/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,106 This file is loaded in full into every session.

When invoked 1,106 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.01106	$0.01106
Opus 5	$0.00553	$0.00553
Sonnet 5	$0.00221	$0.00221
Haiku 4.5	$0.00111	$0.00111

Measured 10d ago against content hash 67bd0d006c76, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

feishu-claude-bridge 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 10d 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 · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Setup Guide for AI Assistants

When a user clones this project and asks you to help set it up, follow these steps.

What This Is

Feishu Claude Bridge — a Node.js daemon that connects Feishu/Lark to Claude Code CLI. Users chat with a bot in Feishu, the daemon calls Claude Code, and streams responses back as real-time cards.

Prerequisites

Node.js >= 20 (node --version)
Claude Code CLI installed and logged in (claude --version)
Feishu enterprise self-built app (see Feishu App Setup below)

Install & Build

cd /path/to/feishu-claude-bridge
npm install
npm run build

npm run build uses esbuild to bundle src/ → dist/daemon.mjs.

Configure

cp config.env.example config.env

Edit config.env:

# ── Required ──
CTI_FEISHU_APP_ID=cli_xxxxxxxxxx
CTI_FEISHU_APP_SECRET=xxxxxxxxxxxxxxxx
CTI_DEFAULT_WORKDIR=/path/to/your/project

# ── Optional ──
CTI_FEISHU_DOMAIN=feishu            # "feishu" or "lark"
CTI_DEFAULT_MODE=code               # code / plan / ask
CTI_FEISHU_REQUIRE_MENTION=true     # Require @bot in group chats
# CTI_FEISHU_ALLOWED_USERS=ou_xxx   # Access control (comma-separated)
# CTI_AUTO_APPROVE=true             # Auto-approve all tool permissions
# CTI_CLAUDE_CODE_EXECUTABLE=/path/to/claude  # Override CLI path

# ── Third-party API provider (optional) ──
# ANTHROPIC_API_KEY=your-key
# ANTHROPIC_BASE_URL=https://your-provider.com/v1
# ANTHROPIC_AUTH_TOKEN=your-auth-token

Feishu App Setup

In the Feishu Open Platform:

Create enterprise self-built app
Enable Bot capability
Go to Events & Callbacks → select Use persistent connection (WebSocket)
Subscribe to event: im.message.receive_v1
Add scopes:
- im:message — Send messages
- im:message.receive_v1 — Receive messages
- im:message:readonly — Read messages
- im:resource — Upload/download resources
- im:chat:readonly — Read chat list
- im:message.reactions:write_only — Typing indicator
- cardkit:card — CardKit v2 streaming cards
Publish app version

Read the full file on GitHub · 130 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.

10d ago First seen · 130 lines · 1,106 tokens per session scan A 67bd0d006c76

Subscribe to this mod's changes

feishu-claude-bridge CLAUDE.md is an instructions file published in the GitHub repository PI-33/feishu-claude-bridge (54 stars, last pushed 5mo ago), licensed MIT. It adds 1,106 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 2026-08-30.

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

feishu-claude-bridge: Instructions file for Claude Code