qa-whitebox-agent

qa-whitebox-agent is an agent for Claude Code from leee880619-commits/ClaudeCode-Harness-Setup-Assistant. It costs 34 tokens per session (336 once invoked), scanned A, original, Apache-2.0.

A white-box quality-assurance agent that checks implemented code by inspecting its source, running tests, and reviewing the code.

In plain words
What is it for?
Use it after implementation to run the project’s checks, review type and pattern consistency, look for workaround signals, and write a PASS or FAIL report without changing code.
Why use it?
It provides a structured check for broken types, lint or test failures, missed plan steps, and temporary fixes that may hide problems. White-box testing means checking the inside of the code, not only its external behaviour.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Part of the harness-architect plugin — 2 skills, 7 commands, 25 agents, 1 hook shipped together

Good fit Use it after implementation to run the project’s checks, review type and pattern consistency, look for workaround signals, and write a PASS or FAIL report without changing code.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/leee880619-commits/claudecode-harness-setup-assistant/qa-whitebox-agent
Install

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.

Clone the repo
git clone --depth 1 https://github.com/leee880619-commits/ClaudeCode-Harness-Setup-Assistant

Made for: Claude Code.

Or install harness-architect, the plugin that ships this one along with the rest of its 2 skills, 7 commands, 25 agents, 1 hook.

Wrote 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.

agentmods badge for qa-whitebox-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-whitebox-agent/github.svg)](https://agentmods.dev/agents/leee880619-commits/claudecode-harness-setup-assistant/qa-whitebox-agent)
Your own site
<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.

agentmods 80×15 button for qa-whitebox-agent

Your own site · 80×15
<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>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 336 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash bb6b4f1eb41f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

.claude/templates/workflows/strict-coding-6step/agents/qa-whitebox-agent.md · 28 lines

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
Changes

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.

  1. 9d ago First seen · 28 lines · 34 tokens per session scan A bb6b4f1eb41f

Subscribe to this mod's changes

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.