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-mcp-indexgit 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-mcp-index)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-mcp-index"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-mcp-index/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-mcp-index"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-mcp-index.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 | $0.00069 | $0.02776 |
| Opus 5 | $0.00034 | $0.01388 |
| Sonnet 5 | $0.00014 | $0.00555 |
| Haiku 4.5 | $0.00007 | $0.00278 |
Grade A, and why
mandu-mcp-index 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 11d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu MCP Index
@mandujs/mcp 는 약 108 개의 MCP 도구를 노출합니다. 이 문서는
flat palette 가 아니라 tiered hierarchy 로 도구를 선택하도록 안내합니다.
핵심 원칙:
- Workflow skill 먼저. 개별 도구가 아닌
mandu-mcp-*workflow skill 을 먼저 본다. - 집계 > 세분. 같은 일을 하는 집계 도구가 있으면 그걸 먼저. 실패했을 때만 세분 도구로 drill-down.
- 안전망 먼저.
refactor_*/ 마이그레이션은mandu.history.snapshot+mandu.tx.begin안에서만. - 순서는 강제.
mandu_create_contract→mandu_generate,mandu.history.snapshot→refactor_*.
1. Situation -> Workflow Skill
| 상황 | 먼저 열 workflow skill | 보조 task-shaped skill |
|---|---|---|
| 세션 시작 / "현 상태?" / "무슨 일 있었어?" | mandu-mcp-orient |
— |
| "만들어줘" / 피처·리소스·라우트 추가 | mandu-mcp-create-flow |
mandu-create-feature, mandu-create-api |
| 편집 직후 / stop-hook / "check 해줘" | mandu-mcp-verify |
mandu-debug |
마이그레이션 / 리팩터 / refactor_* |
mandu-mcp-safe-change |
— |
| 배포 / release / "deploy" | mandu-mcp-deploy |
mandu-deploy |
| 에러 / 증상 기반 진단 | mandu-mcp-verify -> drill-down |
mandu-debug |
| Guard 위반 | mandu-mcp-verify -> mandu_guard_explain |
mandu-guard-guide |
| Island / Hydration | mandu-mcp-verify |
mandu-hydration, mandu-slot |
2. Aggregate > Granular — 우선순위 표
한 번에 처리하는 집계 도구가 있으면 그걸 먼저. 실패/불충분할 때만 세분.
| 목적 | 집계 (먼저 호출) | 세분 (drill-down 용도만) |
|---|---|---|
| 테스트 파이프라인 | mandu.ate.auto_pipeline |
mandu.ate.extract, mandu.ate.generate, mandu.ate.run, mandu.ate.heal, mandu.ate.apply_heal |
| 세션 오리엔테이션 | mandu.ai.brief |
mandu_get_architecture, mandu_get_decisions, mandu_list_routes |
| 배포 준비 | mandu.deploy.check |
mandu_guard_check, mandu_validate_contracts, mandu_validate_manifest |
| 배포 미리보기 | mandu.deploy.preview |
mandu_preview_seo, mandu_write_seo_file |
| 구조/진단 | mandu_doctor |
mandu_check_import, mandu_check_location |
| 스캐폴드 | mandu_generate_scaffold (negotiate → scaffold 묶음) |
mandu_add_route, mandu_create_contract, mandu_generate |
| 피처 생성 | mandu.feature.create |
mandu_add_route × n + contract + generate |
| 리소스 생성 | mandu.resource.create |
mandu.resource.addField, mandu_create_contract, mandu_generate |
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.
- 11d ago First seen · 163 lines · 69 tokens per session scan A c4e658eb05af
mandu-mcp-index is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 15d ago), licensed MPL-2.0. It adds 69 tokens to every session and 2,776 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.
Other skills, from other repositories
truecourse-hooks
Install, configure, or remove the TrueCourse pre-commit hook.
init-workspace-documentation
Skill "init-workspace-documentation" from griddynamics/rosetta, covering agent memory.md, agent memory, preventive rules, what worked and what failed.
truecourse-fix
Fix TrueCourse violations that have suggested fixes.
truecourse-list
List TrueCourse violations found in this repository.
plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
validate
Run the full quality gate — tests, lint, build, and cortex-tms validate --strict.