AI Agent를 정의한 역할, 컨텍스트 및 기능을 제공하는 표준화된 오픈 형식.

마구는 무엇입니까?

A 하네스는 AI 에이전트를 제공하는 디렉토리입니다. 세션에서 에이전트로드를 시작합니다 HARNESS.md] 그것의 정체성을 설정; 작업이 도착함에 따라, 그것은 단지 내용이 각 작업이 필요합니다 —progressive disclosure 하네스 수준에 적용.

Top-level 디렉토리 이름은 하네스 작성자에 의해 선택됩니다. skills/ 과 references/ 일반 규칙이지만 필요하지 않습니다 - 도메인에 맞는 모든 구조.

키 개념

# # # # # 해시.md

필수 입력점. YAML frontmatter를 사용하여 간단한 라우팅 몸에 따라:

몸을 최소한 유지 - 모든 활성화에로드하고 작업 상황에 경쟁합니다.

Routing 파일

각 최상위 디렉토리는 ** 라우팅 파일 ** 모든 캡에서 이름을 따서 명명: TOOLS.md] tools/], DATA.md]], 등. 이 컨벤션은 전체 하위 트리를 통해 전파합니다. tools/] 내의 모든 그룹 하위 디렉토리도 TOOLS.md를 사용합니다. Routing 파일은 에이전트가 지점이 내부에 모든 파일을 열지 않고 관련 여부를 결정합니다.

종료 (저장)

Agent Harnesses

A standardized, open format for giving AI agents a defined role, context, and capabilities.

What is a Harness?

A harness is a directory that gives an AI agent everything it needs to fulfill a role. At session start the agent loads HARNESS.md to establish its identity; as tasks arrive, it pulls in only the content each task requires — progressive disclosure applied at the harness level.

my-harness/
├── HARNESS.md          # Required: identity + routing overview
├── .leaf-detectors     # Optional: leaf boundary patterns
├── tools/              # Top-level dirs are named by the harness author
│   ├── TOOLS.md        # Routing file — describes what's in this branch
│   └── query-db/
│       └── SKILL.md
└── data/
    ├── DATA.md
    └── schema.md

Top-level directory names are chosen by the harness author. skills/ and references/ are common conventions but not required — any structure that fits the domain works.

Key Concepts

HARNESS.md

The required entry point. Uses YAML frontmatter followed by a brief routing body:

---
name: Marketing Assistant
description: Helps create and review content across blog, social, and visual channels.
---

You are a marketing assistant. Produce content that is on-brand and channel-appropriate.

- `tools/` — content creation and research capabilities (see TOOLS.md)
- `brand/` — tone, typography, and visual guidelines (see BRAND.md)
- `campaigns/` — active campaign briefs and goals (see CAMPAIGNS.md)

Keep the body minimal — it is loaded on every activation and competes with task context.

Routing Files

Each top-level directory uses a routing file named after it in all-caps: TOOLS.md for tools/, DATA.md for data/, and so on. This convention propagates through the entire subtree — every grouping subdirectory within tools/ also uses TOOLS.md. Routing files let an agent decide whether a branch is relevant without opening every file inside it.

Termination (Leaves)

Two mechanisms mark a directory as a leaf — a terminal point the routing layer does not recurse into:

• .harnessleaf — a file placed in any directory to signal an explicit boundary
• .leaf-detectors — a root-level file defining keyword patterns; e.g. skill=SKILL.md automatically marks any directory containing SKILL.md as a skill leaf

Leaf type names are meaningful: a skill leaf is loaded and executed as an Agent Skill; other types are treated as opaque boundaries.

Loading Model

Relationship to Agent Skills