Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kaixindelele/wechat_agent_bridge_skills --skill wechat-cursor_agent_bridge-skillgit clone --depth 1 https://github.com/kaixindelele/wechat_agent_bridge_skillsWrote 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/skills/kaixindelele/wechat_agent_bridge_skills/wechat-cursor_agent_bridge-skill)<a href="https://agentmods.dev/skills/kaixindelele/wechat_agent_bridge_skills/wechat-cursor_agent_bridge-skill"><img src="https://agentmods.dev/badge/skills/kaixindelele/wechat_agent_bridge_skills/wechat-cursor_agent_bridge-skill/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/skills/kaixindelele/wechat_agent_bridge_skills/wechat-cursor_agent_bridge-skill"><img src="https://agentmods.dev/badge/skills/kaixindelele/wechat_agent_bridge_skills/wechat-cursor_agent_bridge-skill.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 | $0.00084 | $0.02010 |
| Opus 5 | $0.00042 | $0.01005 |
| Sonnet 5 | $0.00017 | $0.00402 |
| Haiku 4.5 | $0.00008 | $0.00201 |
Grade D, and why
wechat-cursor-agent-bridge scanned grade D with 2 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 11d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **关键危险操作**（匹配 `criticalCommandPatterns`，如 `rm -rf /`、`sudo rm`、`mkfs`、`dd if=`）：拒绝后**终止整个 Agent**，因为此类操作不可安全跳过。 Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **关键危险操作**（匹配 `criticalCommandPatterns`，如 `rm -rf /`、`sudo rm`、`mkfs`、`dd if=`）：拒绝后**终止整个 Agent**，因为此类操作不可安全跳过。 How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
微信 ↔ Cursor 侧 Claude Agent 桥接
用微信连接 本机运行的 Claude Agent SDK 进程（与 Cursor / Claude Code 同源工具与权限语义）。你在 Cursor 里熟悉的「工具权限 / 会话 / 项目目录」可与本桥接对齐：将 bridge.config.json 的 cwd 设为 Cursor 工作区根目录，并按需开启 settingSources: ["project"] 以加载 .claude/、CLAUDE.md 与项目技能。
如需在全局 Cursor 对话中被自动召回，可将本目录下的 SKILL.md 复制到 ~/.cursor/skills/wechat-cursor-agent-bridge/SKILL.md（与路径中的 bridge 拼写无关，技能名以 frontmatter 为准）。
如果需要修改和微信桥接的功能代码，可以参考wechat_agent_bridge_skills/openclaw-weixin的原版SDK通信协议和逻辑。
目录说明
| 路径 | 作用 |
|---|---|
templates/ |
可独立运行的 Node 桥接服务（npm 安装依赖后 npm run setup / npm start） |
templates/src/ilink.ts |
微信 ilink（ClawBot）HTTP API：收发消息、媒体加解密 |
templates/src/bridge.ts |
主循环：getupdates + query() + canUseTool 微信确认 |
templates/bridge.config.example.json |
配置模板，复制为 bridge.config.json |
ilink 层与 Tencent openclaw-weixin 对齐
templates/src/ilink.ts 已与官方 SDK 行为对齐（对照 openclaw-weixin/ 与上游 Tencent/openclaw-weixin）：
- 请求头：
iLink-App-Id（package.json顶层ilink_appid，当前为bot）、iLink-App-ClientVersion（由桥接包version计算 0x00MMNNPP）、X-WECHAT-UIN（crypto.randomBytes）。 base_info.channel_version：使用本桥接package.json的version字段（与 openclaw 使用其自身 npm 版本一致）。- CDN 下载：
{cdnBaseUrl}/download?encrypted_query_param=...（不再把encrypt_query_param当作整段 query 拼在主机名后）。 - 长轮询：
getupdates客户端超时返回ret: 0, msgs: []并保留get_updates_buf。 - 扫码：
scaned_but_redirect时切换redirect_host轮询；网络错误时轮询返回wait并重试。 - 可选：若需多地域路由标签，设置环境变量
ILINK_SK_ROUTE_TAG（对应 openclaw 的SKRouteTag）。
前置条件
- Node.js ≥ 18
ANTHROPIC_API_KEY（或 Bedrock / Vertex 等 SDK 支持的认证方式）- 微信侧已完成 ClawBot / ilink 机器人绑定（通过
npm run setup扫码完成）
安装与启动（由 Agent 执行）
cd wechat-cursor_agent_bridge-skill/templates
cp bridge.config.example.json bridge.config.json
# 编辑 bridge.config.json：至少设置 cwd 为 Cursor 项目根目录
npm install
npm run setup # 扫码，生成 credentials.json
npm start # 启动桥接
微信端：权限确认（核心）
当 Agent 请求执行敏感工具时，你会收到一条带说明的权限消息。在 同一会话 中回复以下任一形式：
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- templates/.gitignore 88 B
- templates/bridge.config.example.json 748 B
- templates/credentials.json.example 226 B
- templates/package-lock.json 18 KB
- templates/package.json 544 B
- templates/src/bridge.ts 55 KB runs code
- templates/src/config.ts 4.5 KB runs code
- templates/src/ilink.ts 21 KB runs code
- templates/src/inbound-media.ts 5.4 KB runs code
- templates/src/permission-gate.ts 3.8 KB runs code
- templates/src/qrcode-terminal.d.ts 128 B runs code
- templates/src/setup.ts 4.1 KB runs code
- templates/src/types.ts 6.5 KB runs code
- templates/tsconfig.json 335 B
- 快速启动.md 5.0 KB
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.
- 11d ago First seen · 114 lines · 84 tokens per session scan D 89e8472d8f09
wechat-cursor-agent-bridge is a skill published in the GitHub repository kaixindelele/wechat_agent_bridge_skills (20 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 2,010 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…