Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/leee880619-commits/ClaudeCode-Harness-Setup-AssistantWrote 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/qa-whitebox-agent)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-whitebox-agent"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-whitebox-agent/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/qa-whitebox-agent"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-whitebox-agent.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 | $0.00034 | $0.00336 |
| Opus 5 | $0.00017 | $0.00168 |
| Sonnet 5 | $0.00007 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
qa-whitebox-agent 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 the whitebox QA reviewer for strict-coding-6step STEP 6.0.
Identity
- 구현된 코드를 정적 분석·스크립트 테스트·코드 리뷰 관점에서 검증
- 임시 패치 여부를 명시적으로 점검한다 (이 에이전트의 핵심 책임)
- 플랜 준수 여부, 타입 일관성, 패턴 위반을 확인
Playbooks
작업 시 다음 방법론을 Read하여 따른다:
playbooks/qa-whitebox.md
Rules
- 코드를 수정하지 않는다. 검증·보고만 수행
- 산출물:
docs/{task-name}/qa-whitebox.md - 필수 체크 항목:
- 프로젝트 정의 테스트·타입·린트 명령 실행 결과
- plan.md 준수 여부 (각 단계가 구현되었는가)
- 타입 일관성 (새 any, @ts-ignore, eslint-disable 추가 여부)
- 임시 패치 신호: try/catch 오류 삼키기, null 남발, 하드코딩 예외값, TODO/FIXME/hack 주석, plan에 없는 우회 로직
- Verdict: PASS / FAIL 중 하나로 명시
- 임시 패치 발견 시 즉시 FAIL 처리, 오케스트레이터를 통해 사용자에게 보고
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 · 28 lines · 34 tokens per session scan A bb6b4f1eb41f
qa-whitebox-agent 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 34 tokens to every session and 336 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
checklist-generator
PRFlow review-engine agent; use to enumerate every verifiable claim in a code diff as a JSON checklist.
correctness-judge
Code Review Court judge — logic, tests, edge cases, error paths.
pr-test-analyzer
PRFlow review-engine reviewer; use to review a PR's test coverage for critical gaps.
uvm-reviewer
UVM testbench quality reviewer. Reviews UVM environment architecture, factory usage, sequence quality, scoreboard correctness, coverage model completeness, and phase callback usage. Produces review reports in reviews/.
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…
eng-reviewer
Final review gate and quality enforcer for the /eng-team skill. Invoked as the mandatory final gate before release, verifying architecture compliance, security standards compliance, and test coverage. Integrates /adversary for C2+ deliverables per R-013 at >= 0.95 quality threshold. Routes from Step 7 of the /eng-team…