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 modu-ai/moai-cowork --skill collab-specgit clone --depth 1 https://github.com/modu-ai/moai-coworkWrote 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/collab-spec)<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/collab-spec"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/collab-spec/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/collab-spec"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/collab-spec.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 | $0.00123 | $0.00806 |
| Opus 5.5 | $0.00049 | $0.00322 |
| Sonnet 5.5 | $0.00025 | $0.00161 |
| Haiku 4.5 | $0.00012 | $0.00081 |
Grade A, and why
collab-spec 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 19d 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.
What it actually says
제품 명세와 AI 도입 검토
요청에 따라 references/product-manager.md 또는 references/ai-strategy.md를 읽고 필요한 부분만 적용한다. 자료가 없다는 이유로 제품, 사용자, 팀 규모, 예산, 일정, 예상 성과를 만들어내지 않는다. 확인된 요구와 제안, 미결정 사항을 구분한다.
진행 방법
- 사용자가 해결하려는 문제, 대상 사용자, 원하는 산출물과 제공 자료를 확인한다. 입력이 부족해도 가능한 초안을 먼저 작성하고 중요한 빈칸을 질문으로 남긴다.
- 기존 자료와 접근 가능한 근거에서 요구사항을 뽑는다. 상충하는 요구는 어느 자료에서 왔는지 보여주고 결정이 필요한 쟁점으로 남긴다.
- 사용자 요청 범위에 맞는 문서만 작성한다. PRD 요청에 로드맵·스프린트 계획·회고를 자동으로 붙이지 않는다.
- 각 요구사항은 관찰 가능한 동작과 수용 기준으로 쓴다. 성능·보안·접근성 기준이 필요한 경우 해당 제품의 실제 제약과 검증 방법을 함께 적는다.
- 우선순위는 사용자가 정한 기준으로 매긴다. RICE, MoSCoW 같은 방법은 점수나 분류 근거가 있을 때 선택적으로 쓴다.
- 수치 목표와 일정은 사용자 입력이나 검증된 자료에 있을 때만 기입한다. 없으면 측정 방법, 기준값 수집, 결정 담당자를 제시한다.
PRD 기본 틀
- 배경과 문제: 확인된 사용자 문제와 근거
- 목표와 측정: 지표 정의, 기준값·목표값의 출처 또는 미정 표시
- 범위: 포함·제외 기능, 사용자 흐름
- 요구사항: 식별자, 동작, 우선순위 근거, 수용 기준
- 제약과 의존성: 기술·운영·법적 검토가 필요한 항목
- 결정 대기: 확인할 질문, 담당자, 필요한 자료
AI 도입 전략 요청은 현재 업무와 데이터 접근, 적용 후보, 작은 검증 방법, 비용과 위험, 성과 측정 방식을 정리한다. 실제 데이터 없이 ROI나 성공 확률을 계산하지 않는다.
정부 일반 지원사업 신청서는 moai-consultant:consult-gov-grant, 학술·연구비 과제 신청서는 moai-tutor:education-grant-writer를 사용한다. 문체 검수가 필요하면 moai-coworker:ai-slop-reviewer와 moai-writer:korean-humanize를 선택적으로 사용하되 요구사항과 수치를 바꾸지 않는다.
참고 자료
| 파일 | 사용 시점 |
|---|---|
references/product-manager.md |
PRD·기능 명세·우선순위 요청 |
references/ai-strategy.md |
AI 도입 검토·전략 요청 |
What ships with it
2 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.
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.
- 19d ago Changed · +1 lines 8550b46fb719
- 1mo ago Changed · -70 lines · -57 tokens per session 9e7f63ecc099
- 1mo ago First seen · 113 lines · 180 tokens per session scan A ac0f6d341336
collab-spec is a skill published in the GitHub repository modu-ai/moai-cowork (311 stars, last pushed 17d ago), licensed Apache-2.0. It adds 123 tokens to every session and 806 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
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"…
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…
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…
wrap-up
End-of-session handler: checks if the plan is complete. If complete: quick retrospective, forward follow-up prompt, and (in a repo) refresh + clean gone branches. If incomplete: skip cleanup, emit resume prompts. Cleanup needs a repo; rest doesn't.
track-followups
Record triaged follow-up work where it'll be seen: create the item in Vikunja or Zammad (incidents), deduplicating first and reporting the id. Use when session work outlives it or items were triaged elsewhere. Never opens a GitHub issue.