mandu-lint

mandu-lint is a skill for Claude Code, Codex from konamgil/mandu. It costs 53 tokens per session (2,116 once invoked), scanned A, original, MPL-2.0.

A code-quality checking guide built around linting, type checking, and architecture checks. Linting finds issues such as unused variables, while type checking catches incorrect data types.

In plain words
What is it for?
Use it to set up or run oxlint, check modified code, connect checks to pre-push hooks, and review lint errors or warnings.
Why use it?
It helps catch code-quality, type, and import-rule problems before they reach a commit, push, or continuous-integration build.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to set up or run oxlint, check modified code, connect checks to pre-push hooks, and review lint errors or warnings.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/konamgil/mandu/mandu-lint
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.

Any agent
npx skills add konamgil/mandu --skill mandu-lint
Clone the repo
git clone --depth 1 https://github.com/konamgil/mandu

Made for: Claude Code, Codex.

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 mandu-lint

README.md
[![agentmods](https://agentmods.dev/badge/skills/konamgil/mandu/mandu-lint/github.svg)](https://agentmods.dev/skills/konamgil/mandu/mandu-lint)
Your own site
<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-lint"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-lint/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 mandu-lint

Your own site · 80×15
<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-lint"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,116 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00053 $0.02116
Opus 5 $0.00026 $0.01058
Sonnet 5 $0.00011 $0.00423
Haiku 4.5 $0.00005 $0.00212

Measured 10d ago against content hash bbe6a1322ea3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mandu-lint 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.

docs/archive/skills/package-v0/mandu-lint/SKILL.md · 201 lines

How it starts

The opening of the file, as written. The whole thing — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mandu Lint

Mandu 의 lint 레이어는 guard (아키텍처) + typecheck (타입) + lint (코드 품질) 3축 가드레일 중 하나. oxlint (Rust-based, ESLint 대비 50–100× 빠름) 를 기본으로.

가드레일 체계 (꼭 기억할 것)

레이어 도구 무엇을 잡나 비용
guard mandu guard / mandu_guard_check 아키텍처 / 레이어 / import 규칙 ~1s
typecheck mandu check / tsgo 타입 에러 ~7s
lint oxlint / mandu.lint 코드 품질 (no-explicit-any, no-unused-vars, 등) ~500ms
lint --type-aware oxlint --type-aware / mandu guard --type-aware 타입 의존 lint (no-floating-promises) ~3s

세 개 모두 녹색이 된 후에만 commit / push. mandu check 는 이 모두를 종합 실행.

Trigger

  • 파일 편집 후 (특히 대량 수정 / 리팩터)
  • "lint 해줘", "코드 스타일 체크", "warning 줄여줘"
  • lint 에러가 CI 에서 발견된 경우
  • 신규 프로젝트 셋업 / 기존 프로젝트에 lint 미설치 상태

MCP 도구

도구 용도 side effect
mandu.lint 린트 실행 + 에러/경고 카운트 없음 (읽기 전용)
mandu.lint.setup oxlint 설치 + .oxlintrc.json 스캐폴드 + scripts 배선 파일 수정 (destructive)

표준 흐름

1. 신규 프로젝트

mandu init.oxlintrc.json + oxlint devDep + lint 스크립트 + lefthook.yml (pre-push lint + typecheck) 를 기본 포함. 추가 작업 불필요.

2. 기존 프로젝트에 lint 가 없는 경우

mandu.lint.setup({ dryRun: true })   ← 먼저 계획 보기
  → mandu.lint.setup({})              ← 적용
  → mandu.lint({})                    ← 베이스라인 확인

또는 shell:

mandu lint --setup
mandu lint

3. 편집 후 검증

mandu-mcp-verify fast path 에 이미 포함됨:

mandu.ate.auto_pipeline   ← parallel
mandu.guard.check         ← parallel
mandu.lint                ← parallel (신규)
mandu.doctor              ← parallel

4. 자동 수정

절대 oxlint --fix . 를 무차별 실행하지 말 것. 과거에 .toSorted() 변환으로 ES 타겟이 깨진 전례 있음 (docs/tooling/oxc-lint-roadmap.md §"1차 --fix 대참사").

안전한 자동 수정 절차:

  1. 한 룰만 활성화한 임시 config 작성:
    cat > .oxlintrc.fix-type-imports.json <<'EOF'
    {
      "categories": { "correctness": "off" },
      "rules": { "typescript/consistent-type-imports": "warn" }
    }
    EOF
    
  2. 해당 룰만 --fix:
    oxlint --config .oxlintrc.fix-type-imports.json --fix .
    
  3. 즉시 typecheck + 테스트 검증
  4. 커밋
  5. 임시 config 삭제

Read the full file on GitHub · 201 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. 10d ago First seen · 201 lines · 53 tokens per session scan A bbe6a1322ea3

Subscribe to this mod's changes

mandu-lint is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 13d ago), licensed MPL-2.0. It adds 53 tokens to every session and 2,116 once invoked, about $0.0003 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.