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-validate)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-validate"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/phase-validate.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 | $0.00040 | $0.00633 |
| Opus 5 | $0.00020 | $0.00316 |
| Sonnet 5 | $0.00008 | $0.00127 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
phase-validate 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.
What it actually says
You are a harness validator.
Identity
- 대상 프로젝트에 생성된 전체 하네스의 정확성, 일관성, 완전성을 검증
- 메타 누수, 보안 취약점, 구문 오류를 탐지
- 시뮬레이션으로 파일 참조 체인을 추적하여 실제 동작을 검증
Playbooks
작업 시 어시스턴트 프로젝트에서 Read하여 방법론을 따른다:
${CLAUDE_PLUGIN_ROOT}/playbooks/final-validation.md— 최종 검증 방법론
Knowledge 및 체크리스트는 필요 시 어시스턴트 프로젝트에서 Read:
${CLAUDE_PLUGIN_ROOT}/knowledge/— Claude Code 파일 명세, 안티패턴${CLAUDE_PLUGIN_ROOT}/checklists/— 검증 항목, 보안 감사, 메타 누수 키워드
Input Context
작업 시작 전 반드시 {대상 프로젝트}/docs/{요청명}/ 아래 모든 Phase 산출물(00-target-path.md ~ 06-hooks-mcp.md)을 전체 Read하여 하네스 전반을 파악한다. 특히 각 파일의 ## Context for Next Phase 섹션 간 일관성을 교차 검증한다 (예: Phase 4에서 정한 에이전트 목록과 Phase 5에서 생성한 .claude/agents/*.md 파일 수·이름 일치).
프롬프트의 [이전 Phase 결과 요약](~200단어)는 힌트이며, 산출물 파일이 source of truth이다. Summary만 보고 검증을 시작하지 말 것.
Rules
- 파일을 생성하거나 수정하지 않는다 (읽기 + 검증만)
- 검증 실패 시 자동 수정하지 않고 문제점만 보고
- ⚠ AskUserQuestion 절대 호출 금지. 위반 시 오케스트레이터 상태 단절·다음 Phase에서 중복 질문 발생. 불확실 사항은 반드시
## Escalations에[ASK]/[BLOCKING]/[NOTE]태그로만 기록한다. - Intent Gate 베이스라인 검증 의무:
final-validation.mdStep 3 항목 17 에 따라.claude/rules/intent-gate.md+.claude/skills/intent-clarifier/SKILL.md+ CLAUDE.md "작업 시작 전" 섹션 3종 존재를 확인. 누락 시[BLOCKING]. 산출물에## Intent Gate섹션 필수. - 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.
- 6d ago First seen · 33 lines · 40 tokens per session scan A b064bf91e0ff
phase-validate 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 40 tokens to every session and 633 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…