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 agentmods add skills/kimsanguine/hplan/brainstormnpx skills add kimsanguine/hplan --skill brainstormgit 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/brainstorm)<a href="https://agentmods.dev/skills/kimsanguine/hplan/brainstorm"><img src="https://agentmods.dev/badge/skills/kimsanguine/hplan/brainstorm.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 | $0.00070 | $0.02208 |
| Opus 5 | $0.00035 | $0.01104 |
| Sonnet 5 | $0.00014 | $0.00442 |
| Haiku 4.5 | $0.00007 | $0.00221 |
Grade A, and why
brainstorm 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 — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hplan:brainstorm — Validated Brainstorming
Running for: $ARGUMENTS
Core Goal
superpowers:brainstorming과 달리 Phase 0 Worth-Building Check를 먼저 실행해 "만들어야 하는가"를 확인한 뒤 설계 대화를 시작한다.
출력이 설계 문서 1개가 아니라 설계 문서 + Signal Gate Bootstrap 3개 artifact다.
- Phase 0: Worth-Building Check — 3문 PROCEED/WARN 판정
- Phase 1: 대화형 설계 — 1문 1답, 2-3 접근 방식 비교
- Phase 2: Signal Gate Bootstrap —
harness/pain.md씨앗 + 가정 목록 + PRD §1 초안
Trigger Gate
Use This Skill When
- 새 제품·기능·에이전트 아이디어가 있고 설계 전에 검증이 필요할 때
- discover/opp-tree 이전에 빠른 worth-building check가 필요할 때
- deliver/prd 스킬 작성 전 §1 ICP 초안과 §13 가설 씨앗을 미리 준비하고 싶을 때
Route to Other Skills When
- Phase 0에서 PROCEED → 이 스킬의 Phase 1-2 계속
- Phase 2 완료 후 →
deliver/prd스킬로 handoff - Phase 0에서 WARN이고 깊은 증거 수집 필요 →
discover/opp-tree+discover/assumptions - 이미 ICP와 문제가 명확히 정의됨 →
deliver/prd직접 시작
Boundary Checks
- Phase 0의 3문은 차단이 아닌 방향 안내다. WARN = "지금 당장 discover 먼저 권장"이지 STOP이 아님
- Phase 2 출력물은 AI 생성 초안이다. 실제 Signal Gate 증거가 아님 — 실제 인터뷰·관찰로 보강 필요
- 이 스킬은 설계까지만. 구현 시작 판단은 harness-build를 통해서.
Instructions
You are running /hplan:brainstorm for: $ARGUMENTS
Phase 0 — Worth-Building Check
superpowers에 없는 단계. 3문 이하의 질문으로 "만들 가치가 있는가"를 빠르게 확인한다.
아래 3개 질문을 한 번에 하나씩 대화형으로 묻는다:
Q1: "이 문제를 경험한 실제 사람이 특정되나요? (이름·역할·상황을 구체적으로)"
- 구체적 답변 예시: "B2B SaaS CFO, 매주 월요일 오전 수동으로 부서별 지출 분류"
- 추상적 답변 예시: "20-50대 직장인", "바쁜 사람들"
Q2: "지금 그들이 쓰는 workaround(임시 해결책)가 있나요?"
- workaround가 있으면 문제가 실재한다는 신호
- workaround 없음 = 문제가 아직 felt pain이 아닐 수 있음
Q3: "이것이 해결되면 그들의 행동이 구체적으로 어떻게 바뀌나요?"
- 행동 변화가 명확하면 JTBD(Jobs-to-be-Done)가 있다는 신호
판정:
- 3문 모두 구체적 답변 → PROCEED: "충분한 신호가 있습니다. Phase 1 설계 대화로 이동합니다."
- 1-2문 답변이 추상적 → WARN: "증거가 약합니다. Phase 1을 계속하되, 설계 후 discover/opp-tree로 보강을 권장합니다." (계속 진행)
- 3문 모두 추상적 → WARN(강): "증거가 매우 약합니다. discover/opp-tree를 먼저 실행해 기회를 탐색하는 것을 강력히 권장합니다." (진행 여부 사용자 선택)
Phase 1 — 설계 대화
superpowers:brainstorming의 Phase 1과 동일한 구조. 1문 1답으로 설계를 구체화한다.
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 · 229 lines · 70 tokens per session scan A 08a99b1ed724
brainstorm is a skill published in the GitHub repository kimsanguine/hplan (2 stars, last pushed 19d ago), licensed MIT. It adds 70 tokens to every session and 2,208 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 2026-08-31.
Other skills, from other repositories
codex-setup
Initialize sd0x-dev-flow infrastructure for Codex CLI and other non-Claude agents. Generates AGENTS.md, installs the commit-msg hook, copies runner scripts. The pre-push gate is opt-in via --with-push-gate. Use when setting up a new project or after updating skills.
smart-rebase
Smart partial rebase for squash-merge repositories. Auto-detect which commits to keep/drop when base branch was squash-merged into target. Use when: user says 'rebase', 'partial rebase', 'base already merged', 'smart rebase', or /smart-rebase. Not for: simple git rebase (the developer runs it — Claude never executes…
orchestrate
Agent-driven workflow orchestration (v1 report-only). Use when: declaring an intent (audit/research/feature shape) and wanting a planner agent to derive the skill workflow, preview it, and run read-only fanout with fail-closed no-change verification. Not for: executing mutating steps (v1 emits them as…
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).
test-review
Test coverage review via Codex exec. Use when: reviewing test sufficiency, identifying coverage gaps, test quality audit. Not for: generating tests (use codex-test-gen), code review (use codex-code-review). Output: coverage analysis + gap report.