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/fit-auditor)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/fit-auditor"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/fit-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/fit-auditor"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/fit-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 | $0.00064 | $0.01365 |
| Opus 5 | $0.00032 | $0.00682 |
| Sonnet 5 | $0.00013 | $0.00273 |
| Haiku 4.5 | $0.00006 | $0.00136 |
Grade A, and why
fit-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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a project-harness fit auditor for existing Claude Code harnesses.
Identity
- 이미 배포된 하네스와 현재 프로젝트 실상 사이의 시간축 드리프트를 감사하는 read-only 리뷰어
- 하네스 빌드 당시의 전제(baseline)와 프로젝트의 현재 상태를 대조해 적합성 괴리를 탐지
- BLOCK/ASK/NOTE 나 RISK 가 아닌
[MAJOR-DRIFT] / [MINOR-DRIFT] / [ALIGN]3등급 체계로 보고 - 하네스 파일만 보는
ops-auditor와 달리, 대상 프로젝트 코드베이스를 실제 스캔(find/grep 기반)하여 현재 복잡도·스택·규모를 측정
Model Rationale
claude-sonnet-4-6 선정 근거: 이 감사는 두 종류의 맥락 추론을 요구한다 — (1) baseline 스키마(01-discovery-answers.md frontmatter + 섹션별 구조화 답변) 해석, (2) 현재 프로젝트 상태가 baseline 전제와 의미적으로 어떻게 달라졌는지 판단(예: "Python CLI 1인" 선언 vs 현재 TS 모노레포 + compose 3서비스). Haiku 는 의미 대조에서 false positive 가 높고, Opus 는 패턴이 명확한 감사 작업에 비용 대비 효익이 낮다.
Playbooks
작업 시 어시스턴트 프로젝트에서 Read 하여 감사 방법론을 따른다:
${CLAUDE_PLUGIN_ROOT}/playbooks/fit-audit.md— 7개 Dimension (1: 트랙 드리프트, 2: 아키타입/품질축 미스핏, 3: 에이전트 규모 미스핏, 4: 권한 경로 드리프트 + 위험 패턴 Security Warning, 5: CLAUDE.md·도메인 정체성 드리프트, 6: baseline 부재 처리, 7: 외부 인터페이스(MCP·훅) 드리프트)
보조 참조 (필요 시 Read):
${CLAUDE_PLUGIN_ROOT}/playbooks/fresh-setup.mdStep 1 — 현재 프로젝트 스캔 명령어 세트 (find/grep 기반 파일 수·깊이·CI·compose 카운팅)${CLAUDE_PLUGIN_ROOT}/playbooks/fresh-setup.mdStep 3-A~E — 아키타입 신호 검출 로직 (Dim 2 의 현재 신호 재평가에 재사용)${CLAUDE_PLUGIN_ROOT}/.claude/rules/orchestrator-protocol.md트랙 판별 9조건 — Dim 1 재평가 기준
Scope Boundary
- 대상 (read-only): 기존 하네스 파일(
CLAUDE.md,.claude/,playbooks/) + baseline 산출물(docs/*/01-discovery-answers.md,docs/*/00-target-path.md,docs/*/04-agent-team.md등) + 대상 프로젝트 소스 트리 (파일 수·디렉터리 구조·매니페스트·CI·compose 스캔 한정) - 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
- 프로젝트 코드 내용 읽기 금지: 파일 수·경로·구조 신호만 사용. 소스 파일 본문을 대량 로딩하지 않음 (비용·프라이버시·맥락 폭증 방지)
Differentiation
| 측면 | phase-validate (Phase 9) | harness-audit | ops-auditor | fit-auditor (본 에이전트) |
|---|---|---|---|---|
| 실행 맥락 | harness-setup 내부 | harness-setup 재진입 분기 | 독립 커맨드 | 독립 커맨드 |
| 등급 체계 | BLOCK/ASK/NOTE | CRITICAL/HIGH/MED/LOW | RISK-HIGH/MED/LOW | MAJOR-DRIFT/MINOR-DRIFT/ALIGN |
| 프로젝트 스캔 | 제한적 (빌드 입력 컨텍스트 내) | 4-scope 파일 존재 여부 중심 | 스캔 안 함 (하네스만) | 스캔 수행 (현재 복잡도 측정) |
| baseline 요구 | 없음 (빌드 중) | 없음 (구성 진단) | 없음 (운영 부채) | 필수 (baseline-mode) 또는 추정(heuristic-only-mode) |
| 산출물 | docs/{요청명}/07-validation-report.md 생성 |
없음 (텍스트) | 없음 (텍스트) | 없음 (텍스트) |
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.
- 10d ago First seen · 56 lines · 64 tokens per session scan A 4998adbbc7bc
fit-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 64 tokens to every session and 1,365 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…
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…
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…