What is openclaw-wechat CLAUDE.md?

A set of project instructions for developing and operating an OpenClaw WeChat plugin, which connects AI agents to WeCom messaging.

It helps install the plugin, restart its gateway, verify the callback endpoint, inspect logs, and list installed plugins.

It puts installation, restart, webhook checking, logging, and project structure guidance in one place.

How Xueheng-Li/openclaw-wechat configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to Xueheng-Li/openclaw-wechat. 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/Xueheng-Li/openclaw-wechat/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/Xueheng-Li/openclaw-wechat

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/xueheng-li/openclaw-wechat/claude-md/github.svg)](https://agentmods.dev/instructions/xueheng-li/openclaw-wechat/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/xueheng-li/openclaw-wechat/claude-md"><img src="https://agentmods.dev/badge/instructions/xueheng-li/openclaw-wechat/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/xueheng-li/openclaw-wechat/claude-md"><img src="https://agentmods.dev/badge/instructions/xueheng-li/openclaw-wechat/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,977 This file is loaded in full into every session.

When invoked 1,977 The same file — it is already loaded in full.

Security scan A 1 finding. 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	$0.01977	$0.01977
Opus 5	$0.00988	$0.00988
Sonnet 5	$0.00395	$0.00395
Haiku 4.5	$0.00198	$0.00198

Measured 9d ago against content hash 12f037e20a07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

openclaw-wechat CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl https://your-domain/wecom/callback # expect "wecom webhook ok"

CLAUDE.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 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.

Project Overview

openclaw-wechat is a WeCom (Enterprise WeChat) channel plugin for OpenClaw/ClawdBot. It enables AI agents to communicate with users through WeCom's self-built applications, supporting bidirectional messaging with multiple media types.

Forked from dingxiang-me/OpenClaw-Wechat with extensive enhancements.

Commands

# Install as OpenClaw plugin (note: "plugins" plural, not "plugin")
npm install
openclaw plugins install --link /path/to/openclaw-wechat  # --link for local dev (symlink)
openclaw plugins install /path/to/openclaw-wechat          # without --link copies to ~/.openclaw/extensions/

# Run / restart
openclaw gateway restart
# or via launchctl on macOS:
launchctl kickstart -k gui/$(id -u)/ai.openclaw.gateway

# Verify webhook
curl https://your-domain/wecom/callback  # expect "wecom webhook ok"

# View logs
tail -f /tmp/openclaw/openclaw-$(date +%Y-%m-%d).log | grep wecom

# List plugins
openclaw plugins list

No test suite, linter, or build step — ES modules run directly.

Architecture

The plugin is a single-file Node.js ES module (src/index.js, ~1400 lines) that:

Registers an HTTP endpoint (/wecom/callback) handling both GET (webhook verification) and POST (message callbacks)
Decrypts inbound messages using WeCom's AES-256-CBC + SHA-1 signature scheme
Parses XML payloads into structured messages (text, image, voice, video, file, link)
Routes messages through OpenClaw's conversation API
Sends responses back via WeCom's REST API with rate limiting and message segmentation

Entry: index.js → re-exports src/index.js

Key Design Patterns

Token caching with Promise locking — prevents concurrent token refresh race conditions (getWecomAccessToken)
Semaphore-based rate limiting — max 3 concurrent WeCom API requests, 200ms interval
Binary search UTF-8 segmentation — splitWecomText() splits long messages by byte count (2048B limit), not character count
Proxy routing — wecomFetch() wraps fetch() with optional undici.ProxyAgent for isolated networks
Multi-account isolation — per-account token caching via WECOM_<ACCOUNT>_* env var prefixes

Read the full file on GitHub · 135 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.

9d ago First seen · 135 lines · 1,977 tokens per session scan A 12f037e20a07

Subscribe to this mod's changes

openclaw-wechat CLAUDE.md is an instructions file published in the GitHub repository Xueheng-Li/openclaw-wechat (152 stars, last pushed 6mo ago), licensed MIT. It adds 1,977 tokens to every session, about $0.0099 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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

openclaw-wechat: Instructions file for Claude Code