agentmods.dev

oh-my-sage AGENTS.md

Project instructions for a Xiaomi smart-home AI agent with a web application and a Model Context Protocol server, which lets AI assistants call connected tools. They describe its architecture, commands, and manual testing approach.

In plain words
What is it for?
They are for developing the Next.js and TypeScript web app, building the MCP server, running lint and type checks, and carrying out its manual integration tests.
Why use it?
They give contributors the project context and the commands needed to build, check, and run its two modes.

Instructions file for CodexOpenCode

77 7d ago A scan 1,018 tokens original MIT
View the source file allocnode/oh-my-sage
Install

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.

agentmods
npx agentmods add instructions/allocnode/oh-my-sage/agents-md
Clone the repo
git clone --depth 1 https://github.com/allocnode/oh-my-sage

Made for: Codex, OpenCode.

Per session 1,018 This file is loaded in full into every session.
When invoked 1,018 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01018 $0.01018
Opus 5 $0.00509 $0.00509
Sonnet 5 $0.00204 $0.00204
Haiku 4.5 $0.00102 $0.00102

Measured 2d ago against content hash 63865504e4eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oh-my-sage 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 2d 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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md - oh-my-sage

Project Overview

Xiaomi Mijia smart home AI Agent with dual-mode architecture:

  • Web Mode: Next.js 14 + TypeScript + Ant Design + Vercel AI SDK
  • MCP Mode: Model Context Protocol server for AI coding assistants

Communicates with Xiaomi gateway via WebSocket+ECJPAKE. Uses LLM tool-calling for smart home automation.

Key Commands

# Web development
npm run dev              # Start Next.js dev server
npm run build            # Production build

# MCP development  
npm run build:mcp        # Build MCP server only
npm link                 # Link oh-my-sage-mcp command globally

# Quality checks
npm run lint             # ESLint (next/core-web-vitals)
npx tsc --noEmit         # TypeScript strict mode check

# Testing (manual only, no automated framework)
npm run test             # Runs npx tsx src/test.ts
npx tsx <script.ts>      # Run single TypeScript file

Note: No Jest/Vitest. All tests are manual integration tests via tsx.

Dual Architecture

Web Mode (src/)

  • src/app/ - Next.js App Router, API routes, pages
  • src/components/ - React UI (Chat, DevicePanel, etc.)
  • src/server/ - Backend: AI/LLM integration, Agent core, Gateway client, Session store
  • src/shared/ - Types and constants

MCP Mode (src/core/ + src/mcp/)

  • src/core/ - Shared Core library (tools, gateway, types)
  • src/mcp/ - MCP Server implementation
  • dist/mcp/ - Build output for MCP

MCP Development

Building: npm run build:mcp outputs to dist/mcp/mcp/index.js

Global command: npm link creates oh-my-sage-mcp in PATH

Local testing: oh-my-sage-mcp (stdio mode)

Configuration (for OpenCode/Claude/Cursor):

{
  "mcpServers": {
    "oh-my-sage": {
      "command": "npx",
      "args": ["-y", "oh-my-sage-mcp"]
    }
  }
}

Skill System

Progressive disclosure in .agents/skills/:

  • Layer 1: Catalog (name + description, ~50 tokens)
  • Layer 2: Instructions (full SKILL.md via activate_skill tool)
  • Layer 3: Resources (files in references/ via read_skill_file tool)

Read the full file on GitHub · 132 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. 2d ago First seen · 132 lines · 1,018 tokens per session scan A 63865504e4eb

Subscribe to this mod's changes

oh-my-sage AGENTS.md is an instructions file published in the GitHub repository allocnode/oh-my-sage (77 stars, last pushed 7d ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0051 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 2026-08-30.

Code reviewFrontendTesting
Related

Other instructions, from other repositories

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 · 5,182 tokens

buildNext

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

next.js 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

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

spec-kit 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 · 7,040 tokens

langchain 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 · 4,345 tokens