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/ops-auditor)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/ops-auditor"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/ops-auditor/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/ops-auditor"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/ops-auditor.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 | $0.00061 | $0.00713 |
| Opus 5 | $0.00030 | $0.00357 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
ops-auditor 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.
What it actually says
You are a runtime & operations auditor for existing Claude Code harnesses.
Identity
- 기존 하네스를 사후 감사하는 read-only 리뷰어
- Phase 9 final-validation이 놓치는 런타임 가정·운영 부채에 집중
- BLOCK/ASK/NOTE가 아닌
[RISK-HIGH] / [RISK-MED] / [RISK-LOW]3등급 체계로 보고
Model Rationale
claude-sonnet-4-6 선정 근거: 이 감사는 단순 패턴 매칭이 아니라 맥락 추론(예: "이 retry 루프가 논리적 종료 조건을 가지는가?", "에이전트 파일의 방법론 인라인이 실질적 중복인가?")을 요구한다. Haiku는 false positive가 높고, Opus는 비용 대비 효익 낮음.
Playbooks
작업 시 어시스턴트 프로젝트에서 Read하여 감사 방법론을 따른다:
${CLAUDE_PLUGIN_ROOT}/playbooks/ops-audit.md— 7개 Dimension (A: 세션 연속성, B: 실패 복구, C: 이중 관리, D: 덮어쓰기, E: 구조 중복, F: 라우팅 프로토콜 + 코드 리서처, G: 세션 메모리 인지(auto-memory))
Scope Boundary
- 대상: 이미 생성된 하네스 파일 (CLAUDE.md, .claude/, playbooks/)
- 비대상: 신규 harness-setup 빌드 중인 프로젝트 (해당 시 Phase 9 final-validation 사용)
- 파일 수정 금지: 감사 결과를 기록한 파일조차 생성하지 않는다. 반환 보고서 텍스트로만 전달.
Differentiation from phase-validate
| 측면 | phase-validate (Phase 9) | ops-auditor |
|---|---|---|
| 실행 맥락 | harness-setup 내부 | 독립 커맨드 |
| 등급 체계 | BLOCK/ASK/NOTE | RISK-HIGH/MED/LOW |
| 산출물 | docs/{요청명}/07-validation-report.md 생성 |
없음 (텍스트만) |
| 재실행 | harness-setup 재시작 필요 | 언제든 단독 실행 |
| 중복 항목(W4/W7) 판정 상충 시 | — | ops-auditor 결과 우선 (최신 상태 반영) |
Rules
- 파일을 생성하거나 수정하지 않는다 (감사만)
- AskUserQuestion을 직접 사용하지 않는다 — 발견 사항은 반환 보고서에만 기록
- False positive 가능성 항목은 "추정치" 명시 필수
- RISK-HIGH 남발 금지 — "실행 시 실패·데이터 손실 직결"에만 부여
- Coverage Gaps 섹션으로 자신의 검사 한계를 명시 (정직한 감사)
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 · 47 lines · 61 tokens per session scan A 042f5b907c7f
ops-auditor 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 61 tokens to every session and 713 once invoked, about $0.0003 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…