harness-bujang: Instructions file for Claude Code

CLAUDE.md

harness-bujang CLAUDE.md is an instructions file for Claude Code from bjcho4141/harness-bujang. It costs 7,899 tokens per session, scanned A, original, MIT.

A project guide for Harness-Bujang, a package that coordinates multiple coding agents, with instructions in Korean and English. It explains the repository's monorepo layout, where several related packages live together, and its commands.

In plain words
What is it for?
Use it when working on Harness-Bujang's shared agents, templates, plugin, command-line tool, or related build and test commands.
Why use it?
It gives future coding sessions the project context and working rules they need, reducing time spent rediscovering the structure and conventions.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is bjcho4141/harness-bujang's own configuration. It tells Claude Code how to work on harness-bujang 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 harness-bujang configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/cho/Desktop/4141/testtest.

Reuse

Borrowing it

Nothing to install: this file belongs to bjcho4141/harness-bujang. 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/bjcho4141/harness-bujang/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/bjcho4141/harness-bujang

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 harness-bujang CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/bjcho4141/harness-bujang/claude-md/github.svg)](https://agentmods.dev/instructions/bjcho4141/harness-bujang/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/bjcho4141/harness-bujang/claude-md"><img src="https://agentmods.dev/badge/instructions/bjcho4141/harness-bujang/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for harness-bujang CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/bjcho4141/harness-bujang/claude-md"><img src="https://agentmods.dev/badge/instructions/bjcho4141/harness-bujang/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 7,899 This file is loaded in full into every session.
When invoked 7,899 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 $0.07899 $0.07899
Opus 5 $0.03950 $0.03950
Sonnet 5 $0.01580 $0.01580
Haiku 4.5 $0.00790 $0.00790

Measured 9d ago against content hash 47007a72ccb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harness-bujang 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 9d 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 · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — harness-bujang 작업 가이드

다음 세션에서 이 레포에서 작업할 때 빠르게 컨텍스트 잡기 위한 가이드.

프로젝트 정체성

Harness-Bujang (하네스 부장) — Korean-style multi-agent harness director for Claude Code.

  • VibeFlea 6주 운용 후 추출·범용화한 다중 에이전트 오케스트레이션 패키지
  • 디폴트 SQLite (셋업 0) + 옵트인 Supabase (운영용)
  • 한국어 (부장 페르소나) / 영어 (Director) 양쪽 지원
  • 무엇이고 왜인지 자세히는 README.md 참조

모노레포 구조

harness-bujang/
├── shared/                              # Single Source of Truth
│   ├── agents/{ko,en}/                  # 에이전트 18개 × 2 언어
│   └── templates/{ko,en}/               # CLAUDE.md 섹션 + 학습로그 시드
├── packages/
│   ├── plugin/                          # Claude Code Plugin (/plugin install)
│   └── cli/                             # npx harness-bujang (npm publish 대상)
│       ├── src/{index,init,status,chat,adapt,update,scan,template}.ts
│       ├── scripts/prepare-templates.mjs   # shared → templates/ 번들
│       ├── scripts/sandbox-test.sh         # e2e 검증
│       └── templates/                   # 빌드 산출물 (gitignored)
└── README.md                            # 통합 사용자 가이드

0.9.0 이후: packages/template/ (Next.js admin 라우트 + DB 어댑터) 제거. 톡방은 bujang chat standalone localhost viewer 하나로 통일. 사용자 프로젝트 침습 0.

명령어

# 루트
npm install                               # workspace 의존성 (cli만 있음)

# CLI 개발
cd packages/cli
npm run typecheck                         # tsc --noEmit
npm run build                             # prepare-templates + tsup → dist/
npm run dev -- init --target=...          # tsx로 직접 실행
npm run sandbox-test                      # e2e: init → status → chat 전 흐름 검증

# 수동 sandbox 검증
node dist/index.js init --target=/tmp/sandbox --lang=ko --yes
node dist/index.js status /tmp/sandbox
node dist/index.js chat --target=/tmp/sandbox --create   # localhost:7777

# Plugin 테스트 (Claude Code 안에서)
/plugin install bjcho4141/harness-bujang
/bujang-init

작업 컨벤션

  • Git author: bjcho4141 <[email protected]> (로컬 config로 박혀 있음)
  • Push 전: 항상 gh auth switch --user bjcho4141
  • 커밋 메시지: 한국어 본문, 영어 prefix (feat:, fix:, chore: 등)
  • 공동저자: Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>
  • Staging: 와일드카드 (-A, .) 금지. 디렉토리 인자 또는 파일 명시
  • 에이전트 변경 시: shared/agents/ 가 SoT. plugin/agents/ 는 빌드 시 미러링

Read the full file on GitHub · 242 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. 9d ago First seen · 242 lines · 7,899 tokens per session scan A 47007a72ccb4

Subscribe to this mod's changes

harness-bujang CLAUDE.md is an instructions file published in the GitHub repository bjcho4141/harness-bujang (7 stars, last pushed 3mo ago), licensed MIT. It adds 7,899 tokens to every session, about $0.0395 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 2026-08-31.

Related

Other instructions, from other repositories

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

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

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

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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens