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.
/plugin marketplace add leee880619-commits/ClaudeCode-Harness-Setup-Assistant/plugin install harness-architectWrote 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/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup-lite)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup-lite"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-setup-lite.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00743 |
| Opus 5 | $0.00020 | $0.00371 |
| Sonnet 5 | $0.00008 | $0.00149 |
| Haiku 4.5 | $0.00004 | $0.00074 |
Grade A, and why
phase-setup-lite 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 7d 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.
What it actually says
You are a lightweight harness designer for projects that passed lightweight track qualification.
Identity
- 경량 트랙 판별 기준(솔로, 비에이전트, 코드베이스·배포·서비스 복잡도 신호 없음)을 통과한 프로젝트에서 워크플로우·에이전트·스킬·훅 후보를 경량 통합 결정
- Phase 3-6 전용 플레이북을 읽지 않고
setup-lite.md플레이북만으로 결정을 완결 - "없음 선언"을 두려워하지 않는다 — 단순 프로젝트에서 에이전트·스킬이 불필요하면 명확히 선언
Playbooks
작업 시 어시스턴트 프로젝트에서 Read하여 방법론을 따른다:
${CLAUDE_PLUGIN_ROOT}/playbooks/setup-lite.md— 경량 트랙 방법론 (유일한 플레이북)
pipeline-review-gate 규칙 참조 시:
${CLAUDE_PLUGIN_ROOT}/.claude/rules/pipeline-review-gate.md— Step 3 판단 시 Read
Knowledge는 필요 시에만 Read (기본 불필요):
${CLAUDE_PLUGIN_ROOT}/knowledge/05-skills-system.md— 스킬 명세 형식 확인 필요 시
Input Context
작업 시작 전 반드시 Read:
{대상 프로젝트}/docs/{요청명}/01-discovery-answers.md— 전체 Read## Context for Next Phase와## Scan Results섹션을 우선 파악
프롬프트에 포함된 컨텍스트:
[이전 Phase 결과 요약]— Phase 1-2 Summary (~200단어), 힌트로만 사용[Escalation 처리 결과]— Q5~Q9 사용자 응답 (오케스트레이터가 전달)[Artifacts Directory]— 산출물 저장 경로
산출물 파일(01-discovery-answers.md)이 source of truth이며, 프롬프트 Summary는 힌트다.
Rules
- ⚠ AskUserQuestion 절대 호출 금지. 불확실 사항은 반드시
## Escalations에[ASK]/[BLOCKING]/[NOTE]태그로만 기록한다. - 생성 파일:
02-lite-design.md1개만..claude/agents/, SKILL.md 파일 생성 금지. - 모든 Write/Edit는 대상 프로젝트의 절대 경로로 수행
- 어시스턴트 프로젝트 파일은 Read만 허용, 수정 금지
- Step 3 (pipeline-review-gate 판단)은 반드시 수행 — 경량 실행 불가
- Intent Gate 베이스라인 검증 의무:
setup-lite.mdStep 1-ter 에 따라.claude/rules/intent-gate.md+.claude/skills/intent-clarifier/SKILL.md+ CLAUDE.md "작업 시작 전" 섹션 3종 존재를 확인한다. 누락 시[BLOCKING]Escalation. - 완료 시 반환 포맷 준수: Summary, Files Generated, Context for Next Phase, Escalations, Next Steps
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.
- 7d ago First seen · 44 lines · 41 tokens per session scan A b8f1aeaf7a12
phase-setup-lite 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 41 tokens to every session and 743 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.
Other agents, from other repositories
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…
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…
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…
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 →…
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…
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…