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-deploygit 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-deploy)<a href="https://agentmods.dev/skills/konamgil/mandu/mandu-mcp-deploy"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-mcp-deploy/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-deploy"><img src="https://agentmods.dev/badge/skills/konamgil/mandu/mandu-mcp-deploy.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 | $0.00065 | $0.01962 |
| Opus 5 | $0.00032 | $0.00981 |
| Sonnet 5 | $0.00013 | $0.00392 |
| Haiku 4.5 | $0.00006 | $0.00196 |
Grade A, and why
mandu-mcp-deploy 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 9d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mandu MCP Deploy
프로덕션 배포 직전의 fail-fast 파이프라인. 개별 검증 도구를 손으로 나열하는
대신, mandu.deploy.check 와 mandu.deploy.preview 집계 도구를 쓴다.
Trigger
- "배포", "release", "deploy"
- release tag 직전,
git push origin main직전 - 프로덕션 환경 업로드 전
- CI/CD 에서 deploy job 이전
mandu-deploytask-shaped skill 이 활성화될 때
Recipe (순서 고정, 게이트 엄격)
mandu_build ← 프로덕션 빌드 시작
└─> mandu_build_status ← green 대기 (polling)
└─> mandu.deploy.check ← Tier-0 aggregate: guard+contract+manifest 병렬
│ ─ fail → 즉시 중단, deploy_preview 금지
└─> mandu_write_seo_file ← sitemap/robots/meta 확정
└─> mandu.deploy.preview ← 프로덕션 리허설 (Tier-0)
└─> 사용자에게 배포 승인 요청
└─> (사용자 승인) 외부 배포 실행
Step Detail
Step 1 — mandu_build
mandu_build({ profile: "production" })
alias of mandu.build. 프로덕션 번들 생성. 반환에 jobId / status 포함.
이 호출은 비동기일 수 있다 — 즉시 반환 후 Step 2 로 poll.
Step 2 — mandu_build_status (poll until green)
mandu_build_status({ jobId })
alias of mandu.build.status. status ∈ {pending, running, success, failed}.
success→ Step 3failed→ 중단, 빌드 에러 분석 후mandu-mcp-verify로 이동running→ 짧은 간격으로 재호출
CRITICAL: 빌드 failed 이면 mandu.deploy.check 절대 호출하지 않는다.
빌드가 깨진 상태에서 deploy check 를 돌리면 잘못된 positive/negative 가 나온다.
Step 3 — mandu.deploy.check (Fail-Fast Gate)
mandu.deploy.check({ target: "bun" })
반환:
ok: true→ Step 4 로 진행ok: false, blockers: [...]→ 즉시 중단
blockers 예시:
- guard 위반 (레이어, 금지 import)
- contract validation 실패
- manifest 깨짐 (route 누락 / 중복)
각 blocker 는 가리키는 도구가 있다:
- guard →
mandu_guard_explain,mandu_guard_heal(단, safe-change 감싸기) - contract →
mandu_validate_contracts,mandu_create_contract - manifest →
mandu_validate_manifest
blocker 를 고치면 Step 1 부터 재실행. deploy_preview 로 건너뛰지 않는다.
Step 4 — mandu_write_seo_file
mandu_write_seo_file({ target: "sitemap" })
mandu_write_seo_file({ target: "robots" })
mandu_write_seo_file({ target: "meta" })
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.
- 9d ago First seen · 177 lines · 65 tokens per session scan A 0fa94231d98a
mandu-mcp-deploy is a skill published in the GitHub repository konamgil/mandu (46 stars, last pushed 13d ago), licensed MPL-2.0. It adds 65 tokens to every session and 1,962 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
ci-self-heal
A diagnostic guide for analysing failed continuous-integration checks. Continuous integration, or CI, automatically tests and builds code changes; this guide classifies failures and suggests fixes without editing the code.
ci-debugger
A guide for finding the first useful cause of a failed build, test, packaging, deployment, or continuous-integration job. Continuous integration, or CI, automatically checks code in a hosted pipeline.
playwright-testing
E2E testing with Playwright - Page Objects, cross-browser, CI/CD.
tech-debt-ci-review
Codex adapter for deep technical-debt and CI-stability audits. Use when asked to find test theater, flaky tests, missing or mis-scoped tests, brittle CI/toolchain behavior, structural debt blocking green PRs, or a remediation order for opencode-swarm.
scaffold-cli
Scaffolds a TypeScript CLI and npm package with the house toolchain, dual tsdown outputs, CLI contracts, changesets, and publishing templates. Use when asked to "scaffold a CLI" or "start an npm package". For an existing package release use autoship; for existing API ergonomics use dx-audit.
architecture-paradigm-pipeline
Applies pipes-and-filters for sequential data transformations. Use when data flows through discrete stages like ETL, streaming analytics, or CI/CD pipelines.