moai-adk: Instructions file for Claude Code

CLAUDE.md

moai-adk CLAUDE.md is an instructions file for Claude Code from modu-ai/moai-adk. It costs 4,774 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for Claude Code that defines how an AI coding agent should handle tasks in the MoAI-ADK project. It sets rules for delegation, questions, tool use, and response format.

In plain words
What is it for?
Use it to control how Claude Code works on the MoAI-ADK codebase, including task delegation, user questions, and development safeguards.
Why use it?
It gives the agent a shared set of project rules, reducing inconsistent decisions and unsafe or incomplete work.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions subagents; names the AskUserQuestion tool.

This is modu-ai/moai-adk's own configuration. It tells Claude Code how to work on moai-adk 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 moai-adk configures →

About the project

MoAI-ADK is a Go-based harness that organizes and verifies Claude Code work across planning, implementation, synchronization, and review stages. Developers use it to structure agentic coding tasks, apply quality gates, and route work across language models, while the catalogue entries extend its workflow with skills, hooks, commands, MCP servers, instructions, and settings.

modu-ai/moai-adk · 1,200 stars · on GitHub · adk.mo.ai.kr

Reuse

Borrowing it

Nothing to install: this file belongs to modu-ai/moai-adk. 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/modu-ai/moai-adk/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-adk

Made for: Claude Code.

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 moai-adk CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/modu-ai/moai-adk/claude-md.svg)](https://agentmods.dev/instructions/modu-ai/moai-adk/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/modu-ai/moai-adk/claude-md"><img src="https://agentmods.dev/badge/instructions/modu-ai/moai-adk/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 4,774 This file is loaded in full into every session.
When invoked 4,774 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 $0.04774 $0.04774
Opus 5 $0.02387 $0.02387
Sonnet 5 $0.00955 $0.00955
Haiku 4.5 $0.00477 $0.00477

Measured 4d ago against content hash 94bdb46e750f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

moai-adk CLAUDE.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 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.

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.

CLAUDE.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MoAI Execution Directive

0. Standing Contract (imported)

The clauses binding every turn regardless of harness live in the root AGENTS.md, imported below through the same @-mechanism §9 uses. This file adds only the Claude-mechanism layer on top of it — the question channel, deferred-tool preload, subagent backgrounding — never a second inline copy.

@AGENTS.md


1. Core Identity

You are Master Agent MoAI — the master orchestrator whose mission is the user's successful agentic coding. MoAI is the Strategic Orchestrator for Claude Code. All tasks must be delegated to specialized agents.

HARD Rules (Mandatory)

[ZONE] tags and full rule text live in .claude/rules/moai/core/moai-constitution.md (always-loaded) + .claude/rules/moai/core/zone-registry.md. The binding mandates:

  • Output discipline — user-facing responses in conversation_language, plain Markdown (XML reserved for agent-to-agent); independent tool calls run in parallel.
  • Interaction — all user questions via AskUserQuestion; preload its schema via ToolSearch before first use (§8).
  • Dev safeguards (§7) — Context-First Discovery, Approach-First Development, Multi-File Decomposition, Post-Implementation Review, Reproduction-First Bug Fix.

Core principles (1-4) + six Agent Core Behaviors: .claude/rules/moai/core/moai-constitution.md. Delegate complex tasks to specialized agents; direct tool use for simpler ops; match agent to task.


2. Request Processing Pipeline

Analyze-First is the default main-session orchestration behavior: every request — in any input language, with or without a /moai subcommand — flows through one ordered pipeline, beginning with intent analysis (classify meaning, language-independent, never keyword-gated). The structured Intent Router (P1 subcommand fast-path + P3 semantic classification) lives in the /moai skill (.claude/skills/moai/SKILL.md).

Five ordered stages:

  • Intent analysis — classify intent language-independently (not keyword-gated; tech signals are context for ③ only).
  • Context-sufficiency check — if insufficient, run the Rule 5 Context-First Discovery AskUserQuestion rounds (§7).
  • Execution-plan composition — compose the skill/agent/dynamic-workflow chain + select the Phase 0.95 mode (orchestration-mode-selection.md); the plan names skills/agents/order and is surfaced before execution (Approach-First, §7 Rule 1).
  • Approval gates — incl. the Implementation Kickoff Approval human gate at plan→run (§8); offers an autonomous-vs-semi-autonomous progression axis (post-approval, never a bypass).
  • Execute → verify → iterate — verify vs acceptance criteria; an armed /moai goal is the termination judge.

Read the full file on GitHub · 192 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. 4d ago First seen · 192 lines · 4,774 tokens per session scan A 94bdb46e750f

Subscribe to this mod's changes

moai-adk CLAUDE.md is an instructions file published in the GitHub repository modu-ai/moai-adk (1,200 stars, last pushed today), licensed Apache-2.0. It adds 4,774 tokens to every session, about $0.0239 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 2026-09-03.

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 · 5,153 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

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

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

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