Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/modu-ai/moai-coworknpx agentmods add skills/modu-ai/moai-cowork/projectWrote 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/modu-ai/moai-cowork/project)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/project"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/project/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/modu-ai/moai-cowork/project"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 221 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 351 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00475 | $0.11011 |
| Opus 5 | $0.00237 | $0.05505 |
| Sonnet 5 | $0.00095 | $0.02202 |
| Haiku 4.5 | $0.00047 | $0.01101 |
Grade A, and why
project 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 5d 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 — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
project — 프로젝트 초기화 단일 진입점
사용자는 이 프로젝트에서 무엇을 할지 말해주면 됩니다. /project가 소크라테스 인터뷰로 맥락을 파악하고, 설치된 AI 코워커 플러그인을 스캔해 프로젝트 전용 커스텀 에이전트와 스킬 체인을 설계한 뒤 AGENTS.md(폴더 지침 정본)와 이를 불러오는 CLAUDE.md, 그리고 .claude/agents/를 생성합니다.
개요
이 스킬은 모든 Claude Cowork(Desktop) 프로젝트의 슈퍼 오케스트레이터/어드바이저다. conversation_language로 사용자와 대화하며, 모든 사용자 확인은 AskUserQuestion로만 수행한다(자유 서술형 질문 금지). 이 스킬이 생성하는 하위 에이전트는 사용자에게 직접 질문하지 않고 blocker report만 반환한다(subagent 경계 원칙).
커버리지: 코워커·작가·스토리·마케터·미디어·셀러·사무관·데이터 애널리스트·법무·재무·인사·CS·컨설턴트·커리어·튜터·디자이너 — 전 코워커. 개발 프로젝트 초기화는 이 마켓플레이스의 범위 밖이며, 개발 요청이 들어오면 §개발 요청 처리를 따른다.
개요 안내 (첫 만남): 사용자가 /project로 처음 진입하면, 인터뷰에 들어가기 전에 다음을 먼저 출력한다. 재진입 시 생략한다.
안녕하세요, 저는 PM이에요. 이 프로젝트에 필요한 AI 코워커 팀을 꾸리고, 프로젝트 전용 커스텀 에이전트와 작업 흐름을 설계해 드리는 안내자입니다. "이런 일 할 거야"라고만 말하면 알아서 맞는 코워커들을 연결해 드려요. 어떤 일부터 시작할까요?
Socratic Interview (커버리지 기반 · 라운드 무제한)
이 스킬은 사용자에게 이 프로젝트에서 무엇을·어떻게 처리하고 싶은지만 인터뷰한다. 이름·회사 등 글로벌 프로필은 재질문하지 않는다.
[HARD] 질문 총량에 상한을 두지 않는다. 종료를 정하는 것은 라운드 수가 아니라 커버리지다 — 아래 8개 영역이 채워지거나 명시적으로 유예될 때까지 계속 묻는다. 맥락을 얕게 잡으면 그 얕음이 폴더 지침·스킬 체인·이후 모든 산출물에 그대로 복제되고, 되돌리려면 프로젝트를 다시 세워야 한다.
단, 한 번의 호출에 담을 수 있는 양은 런타임이 정한다. 아래 상한은 기계적 제약이지 우리가 정한 정책이 아니다. 그래서 질문을 늘리는 방법은 한 화면에 더 넣는 것이 아니라 라운드를 더 도는 것이다. 질문을 1개씩 쪼개 연속 호출하지 않고, 매 라운드 슬롯을 꽉 채운다.
런타임별 질문 채널 (2026-08-28 확인)
[HARD] 질문 채널은 런타임마다 다르다. 도구 이름을 하드코딩하지 않는다. 현재 세션에 실제로 노출된 도구를 쓴다.
| 런타임 | 질문 도구 | 한 호출 상한 | 근거 |
|---|---|---|---|
| Claude Code | AskUserQuestion |
1 |
Tools reference · Agent SDK |
| Claude Cowork(Desktop) | AskUserQuestion |
동일 | 같은 SDK 위에서 돈다. 다만 렌더링 버그가 열려 있다(아래) |
| ChatGPT Work(Codex) | request_user_input |
1질문 권장·3 초과 금지 × 각 2~3옵션 | request_user_input_spec.rs |
| 서브에이전트 | 없음 | — | 공식: "AskUserQuestion is not currently available in subagents spawned via the Agent tool" |
What ships with it
14 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/agentsmd-generator.md 17 KB
- references/context-collector.md 7.0 KB
- references/cowork-setup.md 14 KB
- references/designer-setup.md 6.6 KB
- references/diagnostic-protocol.md 7.7 KB
- references/evaluation-protocol.md 3.7 KB
- references/execution-protocol.md 5.9 KB
- references/INDEX.md 3.5 KB
- references/init-protocol.md 20 KB
- references/quality-evaluator.md 6.3 KB
- references/router.md 5.5 KB
- references/templates/AGENTS.md.tmpl 12 KB
- references/templates/CLAUDE.md.tmpl 477 B
- references/update-protocol.md 14 KB
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.
- 5d ago First seen · 388 lines · 475 tokens per session scan A 5822b9d8aac2
project is a skill published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 5d ago), licensed Apache-2.0. It adds 475 tokens to every session and 11,011 once invoked, about $0.0024 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 2026-09-03.
Other skills, from other repositories
n8n-prd-generator
Convert discovery call transcripts into concise n8n Automation Blueprints with interactive question flow. USE THIS SKILL WHEN user says "create a blueprint", "generate automation spec", "convert transcript to blueprint", provides discovery call transcripts or client documentation, needs an n8n automation blueprint for…
pipeline-review
Pipeline review and next-action planner. Pulls all prospects from a specified CRM pipeline stage, analyzes every email thread and meeting transcript per prospect, then delivers a concise per-prospect status summary with sales cycle recap, action items (yours and theirs), and contact details, plus a cross-pipeline…
process-interviewer
Relentless process interviewer that extracts a complete, unambiguous plan from the user's head before any building begins. Use when the user wants to plan a complex task, design a process, build a skill, create a workflow, scope a project, or says things like "I want to build", "let's plan", "help me think through"…
setup-post-disco
Interactive onboarding wizard that gets a user fully set up to run the post-disco-followup skill on their own business, whatever they sell. It first gauges what they already have (an existing proposal template, email template, or documented sales process) and builds around that instead of imposing a template. It…
execute
Execute phase — wave-based crew dispatch with critic gates and evidence-based verification.
plan-task
Structured task planning using Work files. Use for any new feature, bug fix, or project that needs a task breakdown before implementation.