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 agentmods add instructions/lw396/wechat-mcp/agents-mdgit clone --depth 1 https://github.com/lw396/wechat-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/lw396/wechat-mcp/agents-md)<a href="https://agentmods.dev/instructions/lw396/wechat-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/lw396/wechat-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 | $0.00539 | $0.00539 |
| Opus 5 | $0.00269 | $0.00269 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
wechat-mcp AGENTS.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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Commits should use present-tense imperatives (`add`, `refactor`, `fix`) and stay under ~72 characters, mirroring history (`add text message sending function...`). Describe rationale and notable impacts in the body. Pull How it starts
The opening of the file, as written. The whole thing — 26 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Source lives at the repository root with main.go, server.go, routes.go, and tool_handlers.go orchestrating the HTTP + MCP bridge. Domain logic is under repository/, grouped by feature (chatroom, contact, message, tables). Transport helpers and generated protobuf code stay in wcferry/. Shared utilities are in pkg/ (SQLite setup, random IDs, file helpers). Keep new modules within this layout; add feature-specific packages beneath repository/ and isolate cross-cutting helpers inside pkg/.
Build, Test, and Development Commands
go mod tidy syncs module dependencies before compiling. go build ./... produces a full build and validates package wiring. Run go run main.go --sdkLibrary <path> --storageDir <data> --port 10888 for local development. Use go test ./... to execute all unit tests. go fmt ./... must run before committing to apply canonical formatting.
Coding Style & Naming Conventions
Follow gofmt output (tabs for indentation, newline at EOF). Use descriptive package-level names (repository/message, pkg/sqlite3); keep exported symbols PascalCase and internal helpers camelCase. Log structured events through logrus or zap and prefer context-driven error wrapping. Filenames should remain lowercase with underscores only when mirroring external specs.
Testing Guidelines
Author _test.go files beside the code they exercise using Go's testing package; table-driven tests are encouraged for handler and repository layers. Aim to cover new repository queries and message flows, and document edge cases using subtests. Execute go test ./... before pushing and attach failure output to PRs when troubleshooting.
Commit & Pull Request Guidelines
Commits should use present-tense imperatives (add, refactor, fix) and stay under ~72 characters, mirroring history (add text message sending function...). Describe rationale and notable impacts in the body. Pull requests need: concise summary, linked issues (e.g. Fixes #123), manual test notes (go run, go test), and screenshots or curl transcripts for API changes. Request review once CI (if configured) is green.
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 First seen · 26 lines · 539 tokens per session scan A 34896b0d8f5b
wechat-mcp AGENTS.md is an instructions file published in the GitHub repository lw396/wechat-mcp (16 stars, last pushed 10mo ago), licensed MIT. It adds 539 tokens to every session, about $0.0027 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 2026-08-30.
Other instructions, from other repositories
WeChat-MCP AGENTS.md
Instructions for BiboyQG/WeChat-MCP, covering repository guidelines, project structure & modules, build, run & development, coding style & naming and testing guidelines.
WeChat-MCP CLAUDE.md
Instructions for BiboyQG/WeChat-MCP, covering claude 系统提示词（wechat mcp） and replytomessagesbychat 使用规则：.
blockrun-mcp AGENTS.md
AGENTS.md instructions for BlockRunAI/blockrun-mcp, covering blockrun mcp, commands, project structure, key dependencies and install in codex.
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
intervals-icu-mcp CLAUDE.md
Instructions for hhopke/intervals-icu-mcp, covering claude.md, project overview, development commands, architecture (quick reference) and tool categories.