Borrowing it
Nothing to install: this file belongs to leee880619-commits/ClaudeCode-Harness-Setup-Assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/leee880619-commits/ClaudeCode-Harness-Setup-Assistant/main/CLAUDE.mdgit clone --depth 1 https://github.com/leee880619-commits/ClaudeCode-Harness-Setup-AssistantWrote 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/leee880619-commits/claudecode-harness-setup-assistant/claude-md)<a href="https://agentmods.dev/instructions/leee880619-commits/claudecode-harness-setup-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/leee880619-commits/claudecode-harness-setup-assistant/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.
<a href="https://agentmods.dev/instructions/leee880619-commits/claudecode-harness-setup-assistant/claude-md"><img src="https://agentmods.dev/badge/instructions/leee880619-commits/claudecode-harness-setup-assistant/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01308 | $0.01308 |
| Opus 5 | $0.00654 | $0.00654 |
| Sonnet 5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade A, and why
ClaudeCode-Harness-Setup-Assistant 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harness-architect (plugin development context)
이 파일은 이 레포에서 Claude Code 세션을 열고 플러그인 자체를 수정하는 기여자(Contributor)용 가이드입니다. 최종 사용자는
/harness-architect:harness-setup슬래시 커맨드만으로 플러그인을 쓰면 되며 이 파일을 볼 필요가 없습니다.
이 레포가 무엇인가
Claude Code용 Apache-2.0 오픈소스 플러그인인 harness-architect의 소스 저장소입니다. 설치 후 사용자는 /harness-architect:harness-setup 으로 9-Phase 오케스트레이션을 시작해 대상 프로젝트의 Claude Code 하네스를 구축합니다.
이 레포에서 개발 시 (contributors only)
claude --plugin-dir .
--plugin-dir 를 쓰면 ${CLAUDE_PLUGIN_ROOT} 가 이 레포 절대 경로로 치환되어, 실제 플러그인 설치 환경과 동일하게 동작합니다.
수정 시 참고할 문서
- 설계 철학·디렉터리 맵·Phase 상세: ARCHITECTURE.md
- 기여 규칙·코드 스타일·테스트: CONTRIBUTING.md
- 변경 이력: CHANGELOG.md
- 항상 적용 규칙:
.claude/rules/*.md(meta-leakage-guard, orchestrator-protocol, output-quality, question-discipline)
중요 원칙 (요약 — 정본은 .claude/rules/*.md)
- AskUserQuestion은 Orchestrator 전용 — 서브에이전트는
Escalations에 기록. - Agent-Playbook 분리 — 방법론은
playbooks/에만 (.claude/skills/금지 — 자동 디스커버리되어 서브에이전트 소환 우회). - Target Project Guardrail — 대상 프로젝트 경로 밖에 쓰기 금지. Claude Code
permissions.deny로 강제 (구ownership-guard.sh훅은 무동작이어서 v1.0.5에서 제거). - No Meta-Leakage — 산출물에 플러그인 자체 규칙/Claude Code 아키텍처 설명 포함 금지. 검증:
scripts/validate-meta-leakage.sh. - 경로 변수 — 플러그인 내부 참조는
${CLAUDE_PLUGIN_ROOT}필수.
요약이 규칙 파일과 어긋나면 규칙 파일이 우선. 요약 수정 시 규칙 파일 동반 갱신 (CONTRIBUTING.md 체크리스트 참조).
금지 / 필수 패턴
- 금지:
Skill(skill: "fresh-setup")— 방법론을 메인 세션이 직접 실행. - 필수:
Agent(subagent_type: "harness-architect:phase-setup", ...)— 서브에이전트 소환 후 playbook을 서브에이전트가 Read하여 실행. 플러그인 매니페스트(plugin.json)에 등록된 모든 에이전트는 런타임에서harness-architect:네임스페이스 prefix가 자동 부여되며, prefix 없이 소환 시Agent type not found에러가 발생한다.
릴리즈 워크플로우
트리거: 사용자가 "main에 강제 푸쉬 허용" / "릴리즈 진행" / "태깅하고 릴리즈" 등 원격 강제 푸쉬를 명시적으로 승인하는 발화를 하면, 아래 단계를 순서대로 자동 수행한다. 중간에 확인 없이 전 단계를 완주한다.
자동 수행 순서
-
버전 결정 — 사용자가 명시하면 그 버전 사용. 미명시 시 현재
plugin.json버전에서 patch +1. -
CHANGELOG.md 업데이트 —
## [Unreleased]바로 아래에## [X.Y.Z] - YYYY-MM-DD섹션 삽입. 이번 세션에서 수정된 파일과 변경 내용을 기준으로 Added/Changed/Fixed 항목 작성.
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.
- 9d ago First seen · 71 lines · 1,308 tokens per session scan A 9492e3ed2641
ClaudeCode-Harness-Setup-Assistant CLAUDE.md is an instructions file published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,308 tokens to every session, about $0.0065 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.
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.
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.
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).
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).
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.
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.