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.
npx skills add konamgil/mandu --skill mandu-lintgit clone --depth 1 https://github.com/konamgil/manduWrote 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/skills/konamgil/mandu/mandu-lint)<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.
<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>- NVIDIA SkillSpector pass
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 | $0.00053 | $0.02116 |
| Opus 5.5 | $0.00021 | $0.00846 |
| Sonnet 5.5 | $0.00011 | $0.00423 |
| Haiku 4.5 | $0.00005 | $0.00212 |
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 1mo 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.
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 은 .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:
- 한 룰만 활성화한 임시 config 작성:
cat > .oxlintrc.fix-type-imports.json <<'EOF' { "categories": { "correctness": "off" }, "rules": { "typescript/consistent-type-imports": "warn" } } EOF - 해당 룰만 --fix:
oxlint --config .oxlintrc.fix-type-imports.json --fix . - 즉시 typecheck + 테스트 검증
- 커밋
- 임시 config 삭제
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.
- 1mo ago First seen · 201 lines · 53 tokens per session scan A bbe6a1322ea3
mandu-lint is a skill published in the GitHub repository konamgil/mandu (47 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 53 tokens to every session and 2,116 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
smiles-validation
Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.
ci-fix-monitor
Codex adapter for monitoring and fixing CI failures on opencode-swarm PRs. Use when diagnosing failed checks, fixing package-check (npm tarball) failures, resolving quality/lint/format errors, fixing macOS cross-platform file I/O failures, or watching a PR until all checks are green.
issue-tracer
Use when asked to trace, investigate, root-cause, reproduce, plan, fix, resolve, close, or prepare a PR for an issue, bug report, defect, regression, failing test, or confusing runtime behavior. This Codex adapter delegates to the canonical protocol at .opencode, which owns the Full-Resolution Contract, reproduction…
guardrail-patterns
Codex adapter for opencode-swarm destructive-command guardrail changes. Use before modifying src/hooks/guardrails.ts, checkDestructiveCommand, dcNormalizeCommand, shell-wrapper parsing, .swarm destructive-command blocking, or guardrails unit/adversarial tests.
performance-optimizer
Agents should invoke this skill for slow code, high CPU/memory, latency, large data processing, algorithmic complexity, profiling plans, benchmarks, or optimization requests. Profiles first and weighs trade-offs before changing code.
network-diagnostics
Agents should invoke this skill for connectivity, DNS, Pi-hole, port reachability, routing, firewall reachability, TLS/network timeouts, or service access failures. Provides structured network troubleshooting commands and interpretation.