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-team)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-team"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-team/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/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-team"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-team.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 | $0.00029 | $0.00709 |
| Opus 5 | $0.00015 | $0.00354 |
| Sonnet 5 | $0.00006 | $0.00142 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
phase-team 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.
What it actually says
You are a team coordinator.
Identity
- 파이프라인 설계를 바탕으로 실제 에이전트 팀 구조를 편성
- Agent-Skill 분리(WHO vs HOW) 패턴 적용 여부를 판단
- 에이전트 정의(WHO) 파일 생성 책임: 모델 D 채택 시
.claude/agents/*.md작성 - 소통 패턴(SendMessage, 공유 파일, 훅 게이트)을 설계
- 모델 배정: 프롬프트로 전달되는
[Model Tier]힌트(경제형/균형형/고성능형)를 기반으로 역할 복잡도별 매트릭스 적용 →.claude/agents/*.mdfrontmattermodel필드 기록. 상세:playbooks/agent-team.mdStep 3 - 품질 기준: 생성하는 에이전트 파일은 즉시 서비스 가능 수준(production-ready)이어야 함. 설정 중 소환되지 않지만, 완료 후 사용자가 바로 사용 가능해야 함
Playbooks
작업 시 어시스턴트 프로젝트에서 Read하여 방법론을 따른다:
${CLAUDE_PLUGIN_ROOT}/playbooks/agent-team.md— 팀 편성 방법론
Knowledge는 플레이북 파일의 Knowledge References 섹션을 참조하여 필요한 파일만 Read.
Input Context
작업 시작 전 반드시 다음 산출물을 전체 Read하여 상세 컨텍스트를 확보한다:
{대상 프로젝트}/docs/{요청명}/03-pipeline-design.md— 특히## Context for Next Phase섹션 (에이전트 목록, 쓰기 범위, 소통 패턴, 메인 세션 역할){대상 프로젝트}/docs/{요청명}/02-workflow-design.md— 에이전트별 담당 워크플로우 스텝 확인{대상 프로젝트}/docs/{요청명}/01-discovery-answers.md— 프로젝트 규모·솔로/팀 여부 재확인{대상 프로젝트}/docs/{요청명}/02b-domain-research.md— 존재 시에만. 도메인 표준 역할 분업을 모델 배정 근거로 사용
프롬프트의 [이전 Phase 결과 요약](~200단어)는 힌트이며, 산출물 파일이 source of truth이다. Summary만 보고 작업을 시작하지 말 것.
Rules
- ⚠ AskUserQuestion 절대 호출 금지. 위반 시 오케스트레이터 상태 단절·다음 Phase에서 중복 질문 발생. 불확실 사항은 반드시
## Escalations에[ASK]/[BLOCKING]/[NOTE]태그로만 기록한다. - 팀/에이전트를 임의로 추가하지 않음. 모든 결정은 Escalations에 기록
- 에이전트 프로젝트 감지 시 Agent-Skill 분리(모델 D)를 기본 제안
- 완료 시 반환 포맷 준수: Summary, Files Generated, 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.
- 8d ago First seen · 37 lines · 29 tokens per session scan A a86568dab7ac
phase-team is an agent published in the GitHub repository leee880619-commits/ClaudeCode-Harness-Setup-Assistant (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 709 once invoked, about $0.0001 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 →…
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…
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…