Borrowing it
Nothing to install: this file belongs to hetiankong/wechat-local-agent-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/hetiankong/wechat-local-agent-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/hetiankong/wechat-local-agent-mcpWrote 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/instructions/hetiankong/wechat-local-agent-mcp/agents-md)<a href="https://agentmods.dev/instructions/hetiankong/wechat-local-agent-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/hetiankong/wechat-local-agent-mcp/agents-md.svg" alt="Measured on agentmods" 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 | $0.01870 | $0.01870 |
| Opus 5 | $0.00935 | $0.00935 |
| Sonnet 5 | $0.00374 | $0.00374 |
| Haiku 4.5 | $0.00187 | $0.00187 |
Grade A, and why
wechat-local-agent-mcp AGENTS.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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent installation contract
This repository installs a local, read-only MCP that lets an Agent query the computer owner's own WeChat history. Follow this document as the authoritative installation runbook. Never ask the user to paste a key, database, account ID, administrator password, or message content into chat.
Non-negotiable safety rules
- Confirm that the user owns or is authorized to access the local WeChat account before proceeding.
- Keep all source databases, verified keys, decoded media, and transcripts on the local machine. Do not upload them to GitHub, issues, logs, or external services.
- Keep SIP enabled. Never run
csrutil disable. - Never re-sign or replace
/Applications/WeChat.app. On macOS, use only thewxkeyshadow copy managed under the user's Library. - Do not capture, pipe, print, or persist the administrator password. The patched macOS bootstrap delegates authentication to the system dialog.
- Local media address lookup is enabled by default. Media derivation may be available for a selected message, but must never run across all media in a timeline. Do not enable network link fetching, OCR, file extraction, or voice transcription unless the user asks for that capability.
- Do not expose this stdio MCP over HTTP/SSE, and do not add send/reply/UI automation tools.
Supported installations
- macOS 14+ on Apple Silicon: full core install, safe interactive key bootstrap, and optional Apple Vision OCR.
- Windows 11 amd64: core install using the upstream Windows runtime's process scan. OCR helper is not provided.
- Linux and Intel macOS: MCP source can run, but no supported WeChat runtime/key acquisition path is bundled. Stop after diagnostics and explain the boundary.
Install workflow
First inspect without changing the machine:
uname -s
uname -m
git status --short
On Windows, use PowerShell equivalents ([Environment]::OSVersion and
$env:PROCESSOR_ARCHITECTURE). Do not continue if this checkout contains
unrelated or suspicious binaries, databases, config files, or keys.
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.
- 4d ago Changed · +23 lines · +266 tokens per session 8845066c404b
- 7d ago First seen · 174 lines · 1,604 tokens per session scan A ba26570558d7
wechat-local-agent-mcp AGENTS.md is an instructions file published in the GitHub repository hetiankong/wechat-local-agent-mcp (1 stars, last pushed 5d ago), licensed MIT. It adds 1,870 tokens to every session, about $0.0093 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.