ai-harness-template: Instructions file for Claude Code

CLAUDE.md

ai-harness-template CLAUDE.md is an instructions file for Claude Code from studioKjm/ai-harness-template. It costs 771 tokens per session, scanned A, original, MIT.

A template for building workflows around AI coding agents, with lightweight Bash and fuller Python versions. It includes reusable commands, agent roles, project checks, and methods for turning ideas into specifications and changes.

In plain words
What is it for?
Use it to initialize an agent workflow, detect a project’s technology stack, enforce checks for secrets and specifications, and choose development methods.
Why use it?
It provides a ready-made structure for guiding agents through planning, implementation, evaluation, debugging, and other development stages.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is studioKjm/ai-harness-template's own configuration. It tells Claude Code how to work on ai-harness-template 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 ai-harness-template configures →

Reuse

Borrowing it

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

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 ai-harness-template CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/studiokjm/ai-harness-template/claude-md.svg)](https://agentmods.dev/instructions/studiokjm/ai-harness-template/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/studiokjm/ai-harness-template/claude-md"><img src="https://agentmods.dev/badge/instructions/studiokjm/ai-harness-template/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 771 This file is loaded in full into every session.
When invoked 771 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 $0.00771 $0.00771
Opus 5 $0.00385 $0.00385
Sonnet 5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 8d ago against content hash 9a439b26f3e9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

ai-harness-template 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 8d 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 · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — AI Harness Template

This is the harness template repository itself.

Project Overview

AI 에이전트 하네스 엔지니어링 + Ouroboros(명세 기반 개발) 통합 오픈소스 템플릿. 두 가지 버전: Lite(bash only) / Pro(Python enhanced).

Rules

  1. Lite는 외부 의존성 없음 — bash/sed/grep만 사용. commands/agents는 마크다운
  2. Pro는 Python 3.11+ — pydantic, pyyaml, aiosqlite, rich, typer
  3. 민감 데이터 제로 — API 키, JWT, DB URL, 비즈니스 로직 절대 포함 금지
  4. 스택 자동 감지 — init.sh가 프로젝트 타입을 알아서 판단
  5. 점진적 채택 — 전부 쓸 필요 없이 개별 컴포넌트 선택 가능

Structure

  • init.sh — Lite 설치 스크립트 (Harness + Ouroboros commands/agents + methodology dispatcher)
  • lib/ — 공유 유틸리티 (detect-stack, render-template, colors, methodology.sh)
  • templates/ — 프로젝트에 복사할 템플릿 파일
  • gates/ — CI/CD 게이트 스크립트 (check-boundaries, check-secrets, check-spec)
  • boundaries/ — Claude Code 권한 프리셋 + hooks
  • commands/ — Ouroboros 슬래시 커맨드 (interview, seed, run, evaluate, evolve, unstuck, pm) + /methodology
  • agents/ — 11개 에이전트 페르소나 정의
  • ouroboros/ — 시드 스펙 템플릿, 모호성 체크리스트
  • methodology/ — 플러그인 시스템 (스키마, 레지스트리, 상태 템플릿)
  • methodologies/ — 번들 메서드 플러그인 13종 (ouroboros, living-spec, parallel-change, bmad-lite, exploration, strangler-fig, incident-review, threat-model-lite, observability-first, rfc-driven, tdd-strict, lean-mvp, mikado-method)
  • feedback/ — 피드백 루프 도구
  • examples/ — 스택별 예시
  • pro/ — Pro 버전 (Python 엔진, CLI, hooks)
  • docs/ — 가이드 (methodology-guide.md, methodology-catalog.md, CODEBASE-GUIDE.md)

Methodology System

하네스 코어는 고정. 메서드는 플러그인으로 사용자가 선택·조합.

/methodology list                           # 사용 가능한 메서드
/methodology use ouroboros                  # 단일 활성화
/methodology compose ouroboros bmad-lite    # 다중 조합

번들 16종:

  • 0→1 / 1→N: ouroboros (default) · living-spec · parallel-change · bmad-lite · lean-mvp · ddd-lite · shape-up
  • 모든 단계: exploration · threat-model-lite · rfc-driven · tdd-strict · bdd
  • 운영 / 시스템: strangler-fig · incident-review · observability-first
  • 리팩터링: mikado-method

자세한 내용은 docs/methodology-guide.md, docs/methodology-catalog.md.

Read the full file on GitHub · 52 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. 8d ago First seen · 52 lines · 771 tokens per session scan A 9a439b26f3e9

Subscribe to this mod's changes

ai-harness-template CLAUDE.md is an instructions file published in the GitHub repository studioKjm/ai-harness-template (43 stars, last pushed 3mo ago), licensed MIT. It adds 771 tokens to every session, about $0.0039 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.