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-debuggit 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-debug)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-debug"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-debug/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-debug"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00037 | $0.01087 |
| Opus 5.5 | $0.00015 | $0.00435 |
| Sonnet 5.5 | $0.00007 | $0.00217 |
| Haiku 4.5 | $0.00004 | $0.00109 |
Grade C, and why
mandu-debug scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
3. `.mandu/` 캐시 삭제: `rm -rf .mandu/generated` How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu Debug
Mandu 프로젝트의 에러를 진단하고 수정하는 8카테고리 트리아지 시스템. 증상 → 수집 → 진단 → 수정 → 검증 순서로 진행합니다.
Triage: 8 Error Categories
| Category | Symptoms | First Check |
|---|---|---|
| Build | bun run build fails, TS errors |
bunx mandu guard arch --ci |
| White Screen | Page loads but blank | Browser console, SSR output |
| Island | Component not interactive | "use client", import path |
| API | 4xx/5xx from endpoints | Route file, Mandu.filling() chain |
| CSS | Styles missing/broken | app/globals.css, Tailwind config |
| Guard | Architecture violations | bunx mandu guard arch |
| HMR | Changes not reflecting | Dev server restart, port conflict |
| Hydration | Mismatch warnings | Server vs client render diff |
Parallel Collection Phase
문제 발생 시 동시에 수집할 정보:
# 1. Guard check (아키텍처 위반 여부)
bunx mandu guard arch --ci
# 2. TypeScript check
bunx tsc --noEmit
# 3. Dev server logs
# 이미 실행 중이면 터미널 출력 확인
# 4. Browser console
# 개발자 도구에서 에러 메시지 확인
MCP 도구로 수집:
mandu_brain_diagnose({ symptoms: "white screen on /dashboard" })
Fix Patterns by Category
Build Failure
bunx tsc --noEmit- TypeScript 에러 위치 확인- Import 경로 확인 (특히
@mandujs/corevs@mandujs/core/client) bun install- 의존성 누락 확인
White Screen
app/layout.tsx에<html>/<head>/<body>태그가 있는지 확인 -> 있으면 제거page.tsx에서 default export 확인- SSR 에러: 서버 로그에서 렌더링 에러 확인
Island Not Working
"use client"디렉티브 확인 (파일 최상단)- Import:
@mandujs/core/client(NOT@mandujs/core) .island.tsx또는.client.tsx파일 확장자 확인island()API로 감싸져 있는지 확인
API Error
route.ts(NOTroute.tsx) 확인Mandu.filling()체인으로 default export 확인ctx.body()await 누락 확인.guard()반환값 확인 (void = 계속, Response = 차단)
CSS Missing
app/globals.css존재 확인- Tailwind v4 import 확인:
@import "tailwindcss" - 프로덕션:
cssPath옵션이 서버에 전달되는지 확인
Guard Violation
bunx mandu guard arch실행- Layer 위반: import 방향 확인 (상위 → 하위만 허용)
mandu.config.ts의 preset 확인
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 · 116 lines · 37 tokens per session scan C 336f641f20bb
mandu-debug is a skill published in the GitHub repository konamgil/mandu (47 stars, last pushed 1mo ago), licensed MPL-2.0. It adds 37 tokens to every session and 1,087 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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.
confirm-failures-are-causally-linked-to-the-task-before-reportin
When delegating a task affected by this skill, include.
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.