shuiyuan-mcp: Instructions file for Codex

AGENTS.md

shuiyuan-mcp AGENTS.md is an instructions file for Codex, OpenCode from dajiaohuang/shuiyuan-mcp. It costs 1,471 tokens per session, scanned A, original, MIT.

Repository instructions for shuiyuan-mcp, a tool that connects an AI coding assistant to the Shuiyuan discussion forum through the MCP standard. They document its login process, project structure, runtime requirements, and earlier engineering decisions.

In plain words
What is it for?
Working on the shuiyuan-mcp codebase, understanding its files and commands, implementing or troubleshooting cookie-based login, and preserving its documented startup and write-mode behavior.
Why use it?
They give contributors the established rules for authentication, saved browser sessions, startup behavior, and project branding. This reduces the chance of changing behavior that the repository intentionally relies on.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md; mentions Codex.

This is dajiaohuang/shuiyuan-mcp's own configuration. It tells Codex and OpenCode how to work on shuiyuan-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything shuiyuan-mcp configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is import type { RegisterFn } from "../types.js";.

Reuse

Borrowing it

Nothing to install: this file belongs to dajiaohuang/shuiyuan-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.

Copy the file
curl -O https://raw.githubusercontent.com/dajiaohuang/shuiyuan-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dajiaohuang/shuiyuan-mcp

Made for: Codex, OpenCode.

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.

agentmods badge for shuiyuan-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dajiaohuang/shuiyuan-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/dajiaohuang/shuiyuan-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dajiaohuang/shuiyuan-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dajiaohuang/shuiyuan-mcp/agents-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.

agentmods 80×15 button for shuiyuan-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dajiaohuang/shuiyuan-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/dajiaohuang/shuiyuan-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,471 This file is loaded in full into every session.
When invoked 1,471 The same file — it is already loaded in full.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.01471 $0.01471
Opus 5 $0.00736 $0.00736
Sonnet 5 $0.00294 $0.00294
Haiku 4.5 $0.00147 $0.00147

Measured 12d ago against content hash 0fd127381d87, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

shuiyuan-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 12d 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.

AGENTS.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - Shuiyuan MCP

This repository is a Shuiyuan-focused fork of Discourse MCP.

  • Upstream style entry: src/index.ts -> dist/index.js (bin: discourse-mcp)
  • Shuiyuan wrappers: src/shuiyuan-login.ts, src/shuiyuan-mcp.ts
  • Node: >=24
  • Package/repo branding: shuiyuan-mcp, io.github.dajiaohuang/shuiyuan-mcp, https://github.com/dajiaohuang/shuiyuan-mcp

Historical Decisions (From Prior Codex Threads)

These are not optional preferences. They are project decisions already made in previous Discourse/Shuiyuan conversations and implemented in code.

  1. Authentication flow is cookie-based for Shuiyuan SSO.
    • First-run login opens a real browser (Playwright) and saves local session state.
    • Default persisted files are under %APPDATA%\\shuiyuan-mcp\\:
      • cookies.json
      • profile.json
      • browser-profile/
  2. Launcher split is intentional.
    • shuiyuan-mcp-login / shuiyuan-mcp-login.exe: interactive login + cookie/profile save.
    • shuiyuan-mcp / shuiyuan-mcp.exe: normal MCP start reusing saved profile.
  3. Shuiyuan start path defaults to write-enabled mode.
    • src/shuiyuan-mcp.ts appends --allow_writes --read_only=false by default.
    • Do not silently remove this behavior unless explicitly requested.
  4. Default site and tools mode for Shuiyuan wrappers are fixed.
    • Site: https://shuiyuan.sjtu.edu.cn
    • Tools mode: discourse_api_only
  5. Read performance work has already been done in discourse_read_topic.
    • format supports: "auto" | "structured" | "raw"
    • auto switches to raw mode for larger reads (request reduction).
    • Raw strategy and caching were added to avoid rate-limit pressure.
  6. Encoding regressions happened before and must be guarded against.
    • Chinese content previously became ? during some script paths.
    • Always verify published title/body by reading back after write operations.
    • Favor UTF-8-safe execution paths (MCP tool call first; avoid fragile inline shell encodings).
  7. Shuiyuan title length constraint is known and must be enforced.
    • Topic title must be <= 48 characters.
    • Shorten before create/update calls instead of retrying after server rejection.
  8. Rules compliance is a first-class requirement.
    • Rules references were deliberately added into README/skills.
    • Keep skills/shuiyuan-mcp/references/rules.md and publishing guardrails in sync with behavior.
  9. Category conventions were established for publishing flows.
    • Technical MCP/tooling posts: category 51.
    • Shuiyuan usage tutorial posts: category 74.
  10. Windows release flow is part of supported product behavior.
    • scripts/build-shuiyuan-exe.ps1 builds dist-win/shuiyuan-mcp-login.exe and dist-win/shuiyuan-mcp.exe.
    • GitHub releases are expected to ship both launchers in a zip.

Read the full file on GitHub · 150 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.

  1. 12d ago First seen · 150 lines · 1,471 tokens per session scan A 0fd127381d87

Subscribe to this mod's changes

shuiyuan-mcp AGENTS.md is an instructions file published in the GitHub repository dajiaohuang/shuiyuan-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,471 tokens to every session, about $0.0074 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.

Related

Other instructions, from other repositories

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.

github/spec-kit · 7,126 tokens

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

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens