Borrowing it
Nothing to install: this file belongs to Facetomyself/wechat-miniapp-re-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/Facetomyself/wechat-miniapp-re-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/Facetomyself/wechat-miniapp-re-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/facetomyself/wechat-miniapp-re-mcp/agents-md)<a href="https://agentmods.dev/instructions/facetomyself/wechat-miniapp-re-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/facetomyself/wechat-miniapp-re-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 | $0.00545 | $0.00545 |
| Opus 5 | $0.00272 | $0.00272 |
| Sonnet 5 | $0.00109 | $0.00109 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
wechat-miniapp-re-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 8d 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Rules
Boundaries
- This repository contains only the MCP server and clean-room protocol/runtime code.
- Third-party binaries, wxapkg samples, extracted projects, WMPF binaries, profiles copied from other tools, captures, cookies, and credentials must stay outside Git.
- Runtime artifacts must be written below the configured workspace root.
- Do not add a GUI, SSE dependency, or an always-on daemon. The stdio process must start without WeChat or Frida targets.
Architecture
- MCP tools use the
wxmp_*prefix. - Dynamic operations require an explicit
session_id; context-specific operations also requirecontext_id. - Session history is multi-session, but the shared WMPF
127.0.0.1:9421runtime slot is fail-safe single-owner because the runtime protocol has no PID/session handshake. Reject concurrent attaches instead of guessing socket ownership. - Unexpected runtime disconnects must retain the MCP session, requeue the same bridge owner, reset only ephemeral CDP state, and preserve evidence/context listeners for reconnect.
- Frida is imported lazily by the runtime adapter.
- Static engines are isolated behind adapters; do not embed GPL implementations into the MIT core.
- Unsupported runtime capabilities must return structured evidence, never synthetic success.
- A connected bridge proves transport only. Debugger/network require successful CDP probes; trace/request hooks require non-zero installed wrappers and are tracked per context.
- Bundled clean-room profiles use canonical
windows-<version>.jsonnames and load before external legacy directories. Third-party profile contents remain outside Git.
Development
- UTF-8 and LF for text files.
- Use the project Node runtime supplied by the parent repository.
- Before commit run:
npm run check,git diff --check, andgit status --short. - New tools require contract tests and README/API updates.
- Changes to public tool schemas require a version bump.
- Generated profile candidates must bind to a module SHA-256 and remain non-injectable until their confidence is promoted with review evidence.
- Acceptance claims must be recorded below
data/acceptance/and passnpm run acceptance; do not represent a shallower Profile gate as full semantic verification. - Real-target validation uses
scripts/live-semantic-gate.mjs. Keep summaries and session artifacts in the configured workspace, and preserve structured failure evidence when a lifecycle gate does not trigger.
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.
- 8d ago First seen · 38 lines · 545 tokens per session scan A 5b9607ea70d3
wechat-miniapp-re-mcp AGENTS.md is an instructions file published in the GitHub repository Facetomyself/wechat-miniapp-re-mcp (5 stars, last pushed 15d ago), licensed MIT. It adds 545 tokens to every session, about $0.0027 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.