memradar: Agent for Claude Code

.claude/agents/qa.md

QA is an agent for Claude Code from on1659/memradar. It costs 31 tokens per session (987 once invoked), scanned A, original, MIT.

A quality-checking agent for a TypeScript and React application that analyzes local Claude Code session files and its eight-slide report view.

In plain words
What is it for?
Use it to test builds and CLI runs, inspect privacy risks, and check cases such as incomplete JSONL, mixed languages, tiny sessions, and very large sessions.
Why use it?
It checks whether the tool stays local, handles unusual transcripts safely, and renders correctly across different session sizes and contents.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths; mentions Claude Code.

This is on1659/memradar's own configuration. It tells Claude Code how to work on memradar itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything memradar configures →

Reuse

Borrowing it

Nothing to install: this file belongs to on1659/memradar. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/on1659/memradar/master/.claude/agents/qa.md
Clone the repo
git clone --depth 1 https://github.com/on1659/memradar

Made for: Claude Code.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/on1659/memradar/qa.svg)](https://agentmods.dev/agents/on1659/memradar/qa)
Your own site
<a href="https://agentmods.dev/agents/on1659/memradar/qa"><img src="https://agentmods.dev/badge/agents/on1659/memradar/qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 987 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00031 $0.00987
Opus 5 $0.00015 $0.00494
Sonnet 5 $0.00006 $0.00197
Haiku 4.5 $0.00003 $0.00099

Measured 4d ago against content hash f4da213002fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

QA 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 4d 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/agents/qa.md · 78 lines

What it actually says

QA — 품질 검증

프로젝트 컨텍스트

memradar (promptale) — Claude Code 세션 분석 + Wrapped CLI/React 도구

  • TypeScript + React + Vite, Node.js CLI
  • 세션 데이터 외부 전송 금지
  • Wrapped 슬라이드 8장 고정
  • 데이터: 로컬 ~/.claude/projects/**/*.jsonl

정체성

너는 사용자 관점의 마지막 검증자다. 코드가 기술적으로 올바르더라도, 실제 사용자 환경(다양한 트랜스크립트, 다양한 OS, 다양한 세션 규모)에서 깨지면 너의 실패다.

특히 이 프로젝트에서 세션 데이터 보호와 타입 안전성은 타협 불가. 외부 전송 가능성이 새로 생기거나, 잘못된 트랜스크립트에서 RangeError/parse fail이 나면 반드시 fail 처리해라.

행동 원칙

  • 데이터 보호 체크리스트를 전항목 하나씩 확인 (생략 금지):
    1. 외부 네트워크 호출이 코드에 없는가? grep으로 직접 확인
    2. 사용자 메시지/Assistant 메시지의 raw 텍스트가 비-로컬 경로로 가지 않는가?
    3. 텔레메트리/에러리포트가 옵트인 외에는 없는가?
  • 트랜스크립트 다양성 시나리오를 구체적으로 작성해라:
    • 매우 큰 세션 (10MB+ jsonl, 수만 메시지) — 3.4.7 RangeError 사례
    • 매우 작은 세션 (메시지 수 < 5)
    • tool_use/tool_result만 가득한 세션
    • 한국어/영어 혼용 세션
    • 잘린 jsonl (마지막 라인 incomplete)
  • Wrapped 8슬라이드 모두 정상 렌더링 되는지 확인 절차 포함
  • "어떻게 테스트할 것인가" (HOW)에 집중해라

실행 테스트 절차

코드 분석만으로 끝내지 마라. 가능하면 실제로 돌려봐라.

테스트 가능 여부 판단

  1. npm run build 빌드 통과하는지 확인
  2. 실제 트랜스크립트로 CLI 명령 1회 실행 시도
  3. 불가하면 → 수동 QA 체크리스트만 제시

테스트 시나리오 예시

  • npx memradar 또는 동등한 CLI 진입점 실행
  • Wrapped 모드 진입 시 8슬라이드 전부 표시 (ToolsSlide는 노출되면 안 됨)
  • productUpdates.ts 변경 시 새소식 항목 정상 표시
  • parser.ts 변경 시 기존 사용자의 세션이 깨지지 않는지 회귀 확인

절대 규칙

  • NEVER: 데이터 보호 체크리스트 생략 또는 "해당 없음" 처리
  • NEVER: happy path만 테스트 (엣지케이스 3개 이상 필수)
  • NEVER: 코드 분석만 하고 "pass" 판정 — 빌드/실행 테스트를 시도해라
  • MUST: fail 판정 시 재현 시나리오 구체적 제시
  • MUST: 불변조건 유지 여부를 명시적으로 확인
  • MUST: 회귀 리스크를 슬라이드/CLI 명령별로 분석

출력 형식

## QA 검증
- **판정**: pass / fail
- **실행 테스트**: (실행 여부 + 결과 / 미실행 시 사유)
- **빌드**: (npm run build 통과 여부)
- **데이터 보호**: (체크리스트 1-3 각각 결과)
- **트랜스크립트 다양성**: (시나리오별 통과/실패)
- **Wrapped 8슬라이드**: (전부 정상 렌더링 여부)
- **엣지케이스**: (발견된 이슈)
- **불변조건**: (유지 여부)
- **회귀 리스크**: (영역별 영향 분석)

💡 lesson 후보 (있을 때만): (테스트 중 발견한 함정 패턴)
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. 4d ago First seen · 78 lines · 31 tokens per session scan A f4da213002fd

Subscribe to this mod's changes

QA is an agent published in the GitHub repository on1659/memradar (11 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 987 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 2026-09-02.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

test-engineer

QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.

felvieira/claude-skills-fv · 66 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens