tiangong-ai-mcp: Instructions file for Codex

AGENTS.md

tiangong-ai-mcp AGENTS.md is an instructions file for Codex, OpenCode from linancn/tiangong-ai-mcp. It costs 593 tokens per session, scanned A, original, MIT.

An operating contract for AI coding agents working on the TianGong AI MCP server. MCP is a standard way for an AI agent to use tools exposed by another program.

In plain words
What is it for?
Routing documentation for planned changes, reading contracts and architecture notes, following development runbooks, and validating work on the MCP server.
Why use it?
It defines the required document-reading order, project boundaries, authoritative sources, and completion checks so changes follow the repository’s governance rules.

Instructions file for CodexOpenCode

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

This is linancn/tiangong-ai-mcp's own configuration. It tells Codex and OpenCode how to work on tiangong-ai-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 tiangong-ai-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to linancn/tiangong-ai-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/linancn/tiangong-ai-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/linancn/tiangong-ai-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 tiangong-ai-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/linancn/tiangong-ai-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/linancn/tiangong-ai-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 593 This file is loaded in full into every session.
When invoked 593 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 $0.00593 $0.00593
Opus 5 $0.00296 $0.00296
Sonnet 5 $0.00119 $0.00119
Haiku 4.5 $0.00059 $0.00059

Measured 10d ago against content hash 42ca8553897c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

tiangong-ai-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 10d 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 · 68 lines

What it actually says

TianGong AI MCP Agent Contract

This repository owns the MCP server surface for TianGong AI. Workspace-level submodule policy remains in the root workspace; MCP implementation and repo-local documentation belong here.

Required Load Order

  1. Read this file.
  2. Read .docpact/config.yaml.
  3. Run docpact route --root . --paths <target-paths> --format json from this repo root for the files you plan to change.
  4. Read the relevant files under _docs/contracts/**, _docs/architecture/**, and _docs/runbooks/**.
  5. Read the implementation files under src/**.

Source Of Truth

  • .docpact/config.yaml: machine-readable governance rules, routing aliases, coverage, document inventory, and freshness policy.
  • README.md, README_CN.md, DEV_EN.md, and DEV_CN.md: user-facing and developer-facing workflow notes.
  • _docs/contracts/repo-contract.md: durable ownership and boundary rules.
  • _docs/architecture/repo-architecture.md: current MCP server topology.
  • _docs/runbooks/development.md: repeatable build, local server, and validation steps.

Hard Boundaries

  • Do not move workspace submodule policy, branch policy, or integration completion rules into this repository.
  • Treat MCP tool schemas, authentication behavior, and response streaming as public integration contracts.
  • Do not commit real Supabase, Upstash, LangSmith, or deployment secrets.

Completion Criteria

  • Relevant docpact route output has been reviewed before code or docs changes.
  • Docs touched by the route result are reviewed or updated.
  • docpact validate-config --root . --strict passes after governance changes.
  • For implementation changes, run the relevant build or server validation from _docs/runbooks/development.md.

Implementation Pointers

For tool names, server entry points, auth, and commands, use _docs/architecture/repo-architecture.md, _docs/runbooks/development.md, and package.json as the maintained references.

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. 10d ago First seen · 68 lines · 593 tokens per session scan A 42ca8553897c

Subscribe to this mod's changes

tiangong-ai-mcp AGENTS.md is an instructions file published in the GitHub repository linancn/tiangong-ai-mcp (4 stars, last pushed 21d ago), licensed MIT. It adds 593 tokens to every session, about $0.0030 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

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

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 · 7,104 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

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