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.
npx agentmods add instructions/konamgil/mandu/agents-mdgit clone --depth 1 https://github.com/konamgil/manduWrote 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/konamgil/mandu/agents-md)<a href="https://agentmods.dev/instructions/konamgil/mandu/agents-md"><img src="https://agentmods.dev/badge/instructions/konamgil/mandu/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 | $0.00721 | $0.00721 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
mandu 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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- mandu CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Project Guide
Overview
Mandu는 Bun 기반의 모던 풀스택 프레임워크입니다.
Package Manager
- Bun 사용 (
bun install,bun run,bun test) - pnpm/npm 아님
Project Structure
packages/
├── core/ # @mandujs/core - 핵심 프레임워크
├── cli/ # @mandujs/cli - CLI 도구
└── mcp/ # @mandujs/mcp - MCP 서버
demo/ # 데모 앱들
Agent-Native Workflow
Mandu는 Agent-Native Fullstack Framework다. 에이전트는 파일을 바로 고치기 전에 설치된 Mandu MCP와 Mandu skills를 먼저 고려해야 한다.
작업 전:
- 작업 도메인을 분류한다: route, API, contract, slot, island, guard, debug, deploy, release, docs.
- 관련 Mandu skill이 있으면 사용한다.
- 관련 Mandu MCP tool이 있으면 source 직접 편집보다 우선한다.
- MCP/skill이 없거나 접근 불가하면 그 사실을 말하고 CLI/source fallback을 쓴다.
도구 선택 기준:
| 작업 | 우선 경로 |
|---|---|
| route/page/API 생성 | MCP route/scaffold tools 또는 mandu-fs-routes, mandu-create-api skill |
| contract 변경 | contract MCP tools, contract validation |
| slot/filling 변경 | mandu-slot skill, slot MCP tools |
| architecture/import 문제 | Guard MCP tools, mandu-guard-guide skill |
| island/hydration 문제 | mandu-hydration skill, hydration/build checks |
| 오류 조사 | mandu-debug skill, mandu_doctor/targeted tests |
| 배포/릴리즈 | release checklist, changeset, check:publish |
상세 프로토콜: docs/guides/07_agent_workflow.md
License
- MPL-2.0 (Mozilla Public License 2.0) 전체 적용
- 수정한 파일은 공개 필수, import해서 만든 앱은 자유
배포 (Release)
이 프로젝트는 Changesets를 사용합니다.
변경사항 기록
bun changeset
# → 변경된 패키지 선택
# → major/minor/patch 선택
# → 변경 내용 설명
버전 업데이트 & 배포
bun run version # 버전 업데이트 + CHANGELOG 생성
bun run publish # npm 배포
# 또는
bun run release # 위 두 명령을 한번에
주의사항
workspace:*의존성은bun run version시 실제 버전으로 자동 변환됨- demo/* 패키지는 배포 대상에서 제외됨 (.changeset/config.json)
Git
- 커밋 메시지에 Co-Authored-By 라인을 포함하지 마라.
Scripts
| 명령어 | 설명 |
|---|---|
bun test |
테스트 실행 |
bun run mandu |
CLI 실행 |
bun changeset |
변경사항 기록 |
bun run version |
버전 업데이트 |
bun run publish |
npm 배포 |
bun run release |
version + publish |
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.
- 4d ago First seen · 93 lines · 721 tokens per session scan A fadb2a228922
mandu AGENTS.md is an instructions file published in the GitHub repository konamgil/mandu (46 stars, last pushed 8d ago), licensed MPL-2.0. It adds 721 tokens to every session, about $0.0036 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.
Other instructions, from other repositories
cli CLAUDE.md
Claude Code instructions for archgate/cli, covering claude.md, technology stack, commands, validation gate and git hooks (git 2.54+).
agentlocks AGENTS.md
AGENTS.md instructions for simke9445/agentlocks, covering repository instructions for agents, product maturity policy, commit policy, branch and merge policy and dependency policy.
coderadius AGENTS.md
Instructions for coderadius-ai/coderadius, covering agents.md, what this is, build & run commands, testing and architecture.
coderadius CLAUDE.md
Instructions for coderadius-ai/coderadius, covering claude.md, what this is, build & run commands, testing and architecture.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.
agentconfig.org AGENTS.md
Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.