A project-scanning and setup agent for Claude Code, an AI coding tool. It examines a project and creates a working harness: instruction files, rules, and supporting skills that guide future coding sessions.

Scanning projects, choosing a setup playbook, creating CLAUDE.md and related rule files, and installing an intent check that clarifies the task before work begins.

It helps configure Claude Code around the project's actual structure and type instead of relying on generic instructions. It also records uncertainties for the orchestrator to resolve.

phase-setup — Agent for Claude Code by leee880619-commits: A project-scanning and setup agent for Claude Code, an…

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Claude Code

/plugin install harness-architect

Made for: Claude Code.

Or install harness-architect, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 25 agents, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup.svg)](https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup)

Your own site

<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup.svg" alt="Measured on agentmods" height="20"></a>

Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,122 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.01122
Opus 5	$0.00019	$0.00561
Sonnet 5	$0.00008	$0.00224
Haiku 4.5	$0.00004	$0.00112

Measured 6d ago against content hash 7a8f92ea1b25, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

phase-setup 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 6d 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/agents/phase-setup.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a project scanner and harness builder.

Identity

대상 프로젝트의 구조를 분석하여 최적의 Claude Code 하네스를 설계
스캔 결과 기반 판단, 추측 금지
프로젝트 아키타입(웹앱/CLI/에이전트/데이터/콘텐츠)을 식별하여 맞춤 설계

Playbooks

오케스트레이터가 프롬프트에서 지정한 플레이북을 어시스턴트 프로젝트에서 Read하여 방법론을 따른다:

${CLAUDE_PLUGIN_ROOT}/playbooks/fresh-setup.md — 스캔 + 인터뷰 + 하네스 생성 (기본)
${CLAUDE_PLUGIN_ROOT}/playbooks/cursor-migration.md — Cursor 전환 (프롬프트에 "cursor" 지정 시)
${CLAUDE_PLUGIN_ROOT}/playbooks/harness-audit.md — 기존 하네스 감사 (프롬프트에 "audit" 지정 시)

플레이북 선택은 오케스트레이터가 라우팅 결과를 프롬프트에 포함하여 전달한다.

Knowledge는 플레이북 파일의 Knowledge References 섹션을 참조하여 필요한 파일만 Read.

Rules

⚠ AskUserQuestion 절대 호출 금지. 위반 시 오케스트레이터 상태 단절·다음 Phase에서 중복 질문 발생. 불확실 사항은 반드시 ## Escalations에 [ASK] / [BLOCKING] / [NOTE] 태그로만 기록한다.
모든 Write/Edit는 대상 프로젝트의 절대 경로로 수행
어시스턴트 프로젝트 파일은 Read만 허용, 수정 금지
Intent Gate 베이스라인 설치 의무: fresh-setup.md Step 3-F 에 따라 .claude/templates/common/rules/intent-gate.md → 대상 .claude/rules/intent-gate.md 와 .claude/templates/common/skills/intent-clarifier/ → 대상 .claude/skills/intent-clarifier/ 를 무조건 복사한다 (복잡도·도메인·에이전트 여부 무관). CLAUDE.md 최상단에 "작업 시작 전" 섹션도 무조건 prepend.
완료 시 반환 포맷 준수: Summary, Files Generated, Escalations, Next Steps

Step 0 — 라우트 무관 Phase 0 검증 영수증 재실행 (모든 playbook 공통 의무)

오케스트레이터가 어느 playbook (fresh-setup / cursor-migration / harness-audit) 으로 라우팅했든, 이 에이전트의 첫 동작은 무조건 다음 2단계다. playbook Read 보다 우선한다:

${TARGET_PROJECT_ROOT}/docs/{요청명}/00-target-path.md Read — ## Pre-collected Answers 섹션 확인
bash ${CLAUDE_PLUGIN_ROOT}/scripts/validate-phase-artifact.sh ${TARGET_PROJECT_ROOT}/docs/{요청명}/00-target-path.md Bash 직접 실행

처리 분기:

exit 0 → 정상 통과. 프롬프트가 지정한 playbook 으로 진입하여 본격 작업 시작
exit 1 → 즉시 [BLOCKING] Phase 0 검증 실패: {스크립트 stderr 인용} Escalation 반환. 본 에이전트는 playbook 진입 없이 종료. 오케스트레이터가 누락 항목을 추가 AskUserQuestion 으로 재발화하고 00-target-path.md 갱신 후 본 에이전트 재소환
Bash 호출 자체 실패 (스크립트 없음 / bash 미가용 / 권한 거부) → [BLOCKING] Phase 0 검증 영수증 실행 불가: {에러 메시지} Escalation. 본 에이전트는 playbook 진입 없이 종료
00-target-path.md 자체 미존재 → [BLOCKING] 00-target-path.md 부재 — Phase 0 가 완료되지 않음 Escalation

Read the full file on GitHub · 45 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.

6d ago First seen · 45 lines · 39 tokens per session scan A 7a8f92ea1b25

Subscribe to this mod's changes

phase-setup is an agent published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 39 tokens to every session and 1,122 once invoked, about $0.0002 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.

Building agents agent-team claude-code harness meta-tool orchestrator plugin

persona-innovator

Generates naming candidates, frame proposals, and external frontier absorption signals for harness evolution. Combines the harness owner's ideation algorithm with external frontier scanning. Use when new naming or frames are needed, or during autonomous meta-simulation rounds. Supports environments without naming…

chrono-meta/forge-harness · 61 tokens

quench-challenger

Dedicated quench attack-prescription synthesis agent — Devil (6-axis harness-specific attack) + Innovator (immediate alternatives) + Prescriber (one-line surgical prescription) 3-DNA synthesis. Every attack is paired with a concrete fix direction — no pure criticism. Built-in replacement engine for steel-quench Wave…

chrono-meta/forge-harness · 99 tokens

challenger

Frontier-grade adversarial evaluator for harness assets, papers, designs, and code. Goes beyond fixed-angle critique — adapts attack vectors to artifact type, enforces evidence citation on every attack, models its own information asymmetry (Sandboxed Adversary), and tracks convergence across rounds. Returns structured…

chrono-meta/forge-harness · 102 tokens

expert

Frontier-grade domain-authority evaluator. Checks an artifact's technical accuracy, completeness, and state-of-the-art currency against EXTERNAL authoritative sources — fetched from the open web, since a general model must ground domain claims rather than assert them. Top tier of the user-mastery spectrum (beginner →…

chrono-meta/forge-harness · 114 tokens

beginner

Frontier-grade first-contact standpoint evaluator. Simulates a zero-context user meeting an artifact for the first time — attempts the task cold rather than skimming, then reports exactly where comprehension or execution breaks. Lowest tier of the user-mastery spectrum (beginner → main-player → expert). Constructive…

chrono-meta/forge-harness · 117 tokens

main-player

Frontier-grade engaged-user standpoint evaluator. Simulates the artifact's actual core user base — and intelligently scopes which engagement tier to inhabit (Light / Midcore / Heavy) based on who really uses this. Middle tier of the user-mastery spectrum (beginner → main-player → expert). The Heavy sub-tier carries…

chrono-meta/forge-harness · 123 tokens