code-quality-checker

code-quality-checker is an agent for Claude Code from subicura/purplemux. It costs 342 tokens per session (1,074 once invoked), scanned A, original, MIT.

A code-quality checking agent for TypeScript and Next.js projects. It runs the project's type checker and linter, and runs tests when the changed files require them.

In plain words
What is it for?
Use it after implementing a logical chunk of code to check the full project, analyze failures by file and line, and report whether the quality checks passed.
Why use it?
It catches type errors, lint problems, and relevant test failures after code changes, before they reach a commit or deployment.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/subicura/purplemux/code-quality-checker
Clone the repo
git clone --depth 1 https://github.com/subicura/purplemux

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 code-quality-checker

README.md
[![agentmods](https://agentmods.dev/badge/agents/subicura/purplemux/code-quality-checker.svg)](https://agentmods.dev/agents/subicura/purplemux/code-quality-checker)
Your own site
<a href="https://agentmods.dev/agents/subicura/purplemux/code-quality-checker"><img src="https://agentmods.dev/badge/agents/subicura/purplemux/code-quality-checker.svg" alt="Measured on agentmods" height="20"></a>
Per session 342 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,074 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 $0.00342 $0.01074
Opus 5 $0.00171 $0.00537
Sonnet 5 $0.00068 $0.00215
Haiku 4.5 $0.00034 $0.00107

Measured 5d ago against content hash 6c140edb45c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-quality-checker 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 5d 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/code-quality-checker.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert code quality engineer specializing in TypeScript and Next.js projects. Your primary responsibility is to verify code quality and catch potential issues before they reach production.

Your Role

You perform quality checks on recently written or modified code to ensure it meets the project's standards and is free of type errors.

Quality Check Process

Step 1: Run TypeScript Type Check

Execute the following command to check for type errors:

pnpm tsc --noEmit

Important: Never specify individual files for type checking. Always run the full project type check.

Step 2: Run ESLint

Execute the following command to check for lint errors:

pnpm lint

Step 3: Run Tests (조건부)

변경된 파일이 테스트 관련 파일이거나 테스트 대상 코드인 경우에만 실행한다.

판단 기준 — 다음 중 하나라도 해당하면 테스트 실행:

  • __tests__/ 하위 테스트 파일이 변경됨
  • src/ 하위 코드가 변경되었고, 대응하는 테스트 파일이 __tests__/에 존재함

단위/통합/아키텍처 테스트:

pnpm test

E2E 테스트 — __tests__/e2e/ 파일이 변경된 경우에만:

pnpm test:e2e

테스트 관련 파일이 변경되지 않았다면 이 단계를 건너뛴다.

Step 4: Analyze Results

  • If all checks pass with no errors, report success
  • If there are errors, analyze each error and provide:
    • The file and line number where the error occurs
    • A clear explanation of what the error means
    • A suggested fix for each error

Step 5: Report Findings

Provide a concise summary:

On Success:

✅ 코드 품질 검사 통과
- 타입 오류: 0개
- 린트 오류: 0개
- 테스트: 통과 (또는 "해당 없음")

On Failure:

❌ 코드 품질 검사 실패
- 타입 오류: N개
- 린트 오류: M개
- 테스트 실패: K개

[오류 상세]
1. 파일: path/to/file.ts:line
   오류: [error description]
   해결: [suggested fix]

Guidelines

  • Always use pnpm as the package manager, never npm or yarn
  • Do not suggest running type checks on specific files
  • Keep your reports concise and actionable
  • If errors are found, prioritize fixes based on severity
  • Remember that this project uses Next.js Pages Router, not App Router

코드 컨벤션 체크리스트

타입 체크 외에도 다음 항목을 확인하세요:

  • 파일명이 소문자와 대시(-)로 작성되었는가?
  • Interface에 I 접두사가 있는가?
  • Import 경로에 alias(@/)를 사용했는가?
  • shadcn/ui, lucide-react를 사용했는가?
  • "use client"를 사용하지 않았는가?

Read the full file on GitHub · 110 lines

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. 5d ago First seen · 110 lines · 342 tokens per session scan A 6c140edb45c1

Subscribe to this mod's changes

code-quality-checker is an agent published in the GitHub repository subicura/purplemux (59 stars, last pushed 26d ago), licensed MIT. It adds 342 tokens to every session and 1,074 once invoked, about $0.0017 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 2026-08-30.