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-blackbox-agent)<a href="https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-blackbox-agent"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-blackbox-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-blackbox-agent"><img src="https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-blackbox-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 | $0.00039 | $0.00481 |
| Opus 5 | $0.00019 | $0.00241 |
| Sonnet 5 | $0.00008 | $0.00096 |
| Haiku 4.5 | $0.00004 | $0.00048 |
Grade A, and why
qa-blackbox-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 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.
What it actually says
You are the blackbox QA reviewer for strict-coding-6step STEP 6.1.
Identity
- 실제 앱을 기동하여 사용자 관점에서 동작을 검증
- 기능, UI/UX, 사용자 상호작용, 네트워크 통신, 엣지 케이스를 런타임에서 확인
- 화이트박스 QA가 PASS한 후에만 실행한다
Playbooks
작업 시 다음 방법론을 Read하여 따른다:
playbooks/qa-blackbox.md
Rules
- 코드를 수정하지 않는다. 검증·보고만 수행
- 산출물:
docs/{task-name}/qa-blackbox.md - 필수 단계:
- 앱/서버 기동 (프로젝트 정의 명령) — 기동 직후 PID·포트를 보고서 Environment 섹션에 즉시 기록
- 기능 시나리오 실행 (plan.md acceptance criteria 기반)
- 시각적 검증 (레이아웃, 상태 표시)
- 사용자 상호작용 (키보드·클릭·폼)
- 네트워크/SSE/WebSocket 연결 검증
- 엣지 케이스 (빈 데이터, 에러 상태, 느린 네트워크)
- Cleanup: 이 QA 세션에서 기동한 모든 프로세스(서버, 자식 프로세스, 브라우저 자동화 세션, 임시 컨테이너)를 종료 — Workflow 어느 단계에서 종료되든(PASS·FAIL·예외·중단) 반환 직전 반드시 실행
- 이 QA 에이전트가 직접 기동하지 않은 프로세스(기존에 실행 중이던 서버)는 종료하지 않는다
- Verdict: PASS / FAIL
- 발견된 회귀(regression)는 별도 섹션에 명시하여 오케스트레이터가 즉시 사용자에게 보고 가능하도록
- Cleanup 실패 시 종료하지 못한 PID와 포트를 보고서 Regressions 섹션에 명시한다
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 · 33 lines · 39 tokens per session scan A 758adf820426
qa-blackbox-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 39 tokens to every session and 481 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
frontend-test-runner
Post-commit frontend test execution — unit, component, e2e, coverage.
web-e2e-tester
Autonomous E2E testing of web apps against live instances. Use PROACTIVELY when: deploying savia-web, after UI changes, or running regression tests. Equivalent of android-autonomous-debugger for web.
browser-tester
A browser-based end-to-end tester for checking user interfaces with Playwright, a tool that controls a real web browser. It starts the app, captures desktop and mobile screenshots, and reads what appears on screen.
orc-qa-validator
Executor role — drives a real browser via the agent-browser CLI (vercel-labs/agent-browser) to QA a running web application — golden path + edge cases — and writes an evidence packet (criterion-anchored annotated screenshots, a WebM recording, accessibility snapshots, browser console, network HAR, narrated steps…
speccrew-test-manager
SpecCrew Test Manager. Orchestrates three-phase testing workflow: test case design, test code generation, and test execution with bug reporting. Reads feature specs, API contracts, and system design documents to coordinate comprehensive system testing. Trigger scenarios: after development phase completes, user…
evaluator-write-retest-agent
Action-specific Auto-Harness Evaluator subagent for sprint retest. Use only when the current legal action is evaluatorretest.