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 kimsanguine/hplan --skill ask-teamgit clone --depth 1 https://github.com/kimsanguine/hplanWrote 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/kimsanguine/hplan/ask-team)<a href="https://agentmods.dev/skills/kimsanguine/hplan/ask-team"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/ask-team.svg" alt="Measured on agentmods" 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 | $0.00214 | $0.06262 |
| Opus 5 | $0.00107 | $0.03131 |
| Sonnet 5 | $0.00043 | $0.01252 |
| Haiku 4.5 | $0.00021 | $0.00626 |
Grade A, and why
ask-team 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 8d 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 — 403 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Goal
PM이 "사람에게 질문하고 답을 받는" 기둥을 hplan에 연결한다. ask-team은 번역기다 — 질문/요약 문구만 생성하고, 외부 comms 시스템(Gmail/Notion/Zoom/Slack)을 통한 전달·수집은 MCP 도구에 위임한다. 답을 판단하거나 메시지를 자동 발송하지 않는다.
| 모드 | 책임 | 입력 → 출력 |
|---|---|---|
--mode ask |
질문 초안 작성 (발송 X — 사람이 보냄) | 질문 + 대상 → Gmail create_draft / Notion 코멘트 / Slack 메시지 미리보기 |
--mode pull-answers |
스레드·회의록·코멘트에서 답 수집 | search_threads/Zoom transcript/get-comments/get_thread_replies → harness/answers.md |
--mode digest |
수집한 답 요약 → 라우팅 | harness/answers.md → hplan/decision-log 또는 deliver/ticket-bridge |
--mode review |
PRD 스테이크홀더 리뷰 워크플로우 (리뷰어 배정 + 코멘트 수집 + Signoff audit trail) | PRD 버전 → harness/review-request.md · harness/review-log.md · harness/signoff-record.md |
--mode solo |
Claude가 역할 대리 시뮬레이션 | 질문 + 역할 목록 → 역할별 답변 → harness/answers.md (simulated 태깅) |
기본값:
--mode미명시 → fail loud + 모드 목록. auto-run 금지. solo vs review 분기: 팀원이 없는 솔로 유저는solo(Claude가 역할 대리), 다수 이해관계자가 있는 기업 PM은review(실제 리뷰어 배정 + Signoff)로 분기한다.
능력 차원의 안전장치
Gmail MCP는 create_draft만 노출하고 send 도구가 없다. ask-team은 구조적으로 메일을 자동 발송할 수 없다 — 초안을 만들면 사람이 Gmail에서 검토 후 보낸다. Slack의 post_message는 preview-only로 처리하며 사용자 승인 후에만 호출한다. 확인 게이트가 정책이 아니라 능력으로 강제된다.
Rule 5 준수 경계
| 작업 | LLM 사용 | 근거 |
|---|---|---|
| 질문 문구 생성 (ask) | ✅ 자연어 생성 | Rule 5 허용 |
| 답변 요약 문구 생성 (digest) | ✅ 자연어 생성 | Rule 5 허용 |
| 역할 대리 답변 생성 (solo) | ✅ 자연어 생성 | Rule 5 허용 |
| 대상(수신자) 라우팅 | ❌ 결정론 lookup | harness/team-map.json 매핑 |
| 채널 선택 (Gmail/Notion/Zoom/Slack) | ❌ 결정론 | 매핑 테이블 — LLM if문 금지 |
| 답변 ↔ 질문 매칭 | ❌ 결정론 | question_id + 스레드/코멘트 ID |
| digest 라우팅 (decision-log vs ticket-bridge) | ❌ 결정론 | 답변에 붙은 tag(#decision/#ticket)로 분기 |
자체 점검: 수신자 라우팅·채널 선택·답변 매칭·digest 분기에서 LLM 호출이 감지되면 즉시 fail — Rule 5 위반. "답변이 긍정인지 LLM이 판단" 같은 것도 금지 (요약만, 판단은 사람).
Trigger Gate
Use This Skill When
- "이거 팀에 물어봐줘" / "담당자한테 확인 요청" →
--mode ask - "답변 왔는지 모아줘" →
--mode pull-answers - "받은 답 정리해서 결정 로그/티켓에 붙여줘" →
--mode digest - "PRD 리뷰 돌려야 해" / "리뷰어 배정하고 Signoff 받아줘" / "이해관계자 승인 추적" →
--mode review - "팀원 없는데 혼자 검토해줘" / "CTO 관점으로 봐줘" →
--mode solo - "ask-team 처음 세팅하고 싶어" / "팀원 연락처 등록" →
--mode init
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.
- 8d ago First seen · 403 lines · 214 tokens per session scan A c2602d0279d4
ask-team is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 22d ago), licensed MIT. It adds 214 tokens to every session and 6,262 once invoked, about $0.0011 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 2026-08-31.
Other skills, from other repositories
create-request
Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…
req-analyze
A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.
recap-ask
Interactive Q&A over an existing recap document. Use when: user wants to ask follow-up questions about a briefing-recap- .md produced by /recap-doc, with recap-bounded context + out-of-scope redirect + optional promote-to-request. Not for: generating a new recap (use /recap-doc), general project Q&A (use /ask), code…
recap-doc
Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…
runbook
Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).
jira
Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).