brainstorming

A design-first guide for new features, creative work, and implementation. TDD means test-driven development: writing tests to describe expected behavior before or alongside the code.

In plain words
What is it for?
Use it to inspect project context, ask focused questions, compare approaches, write a specification, and then hand the approved design to planning.
Why use it?
It helps clarify requirements and get a design agreed before planning and implementation begin.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/this-hw/claude-code-kit/brainstorming
Any agent
npx skills add This-HW/claude-code-kit --skill brainstorming
Clone the repo
git clone --depth 1 https://github.com/This-HW/claude-code-kit

Made for: Claude Code, Codex.

Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,059 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00043 $0.01059
Opus 5 $0.00022 $0.00530
Sonnet 5 $0.00009 $0.00212
Haiku 4.5 $0.00004 $0.00106

Measured 2d ago against content hash 119c35a9277b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

brainstorming 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 2d 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.

plugins/common/skills/brainstorming/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Brainstorming

설계 승인 없이 plan-task를 invoke하거나 코드를 작성하면 안 됩니다.

체크리스트

진입 즉시 ToolSearch("select:TaskCreate,TaskUpdate,TaskList")로 Task 도구를 로드한 후,

Task 도구가 없으면 멈추지 말고 대체 경로로 간다ToolSearch가 Task 계열을 반환하지 않는 호스트/세션이 있다(F-038). 그때는 ./scripts/checklist.sh 기반 durable checklist로 추적한다. 규율 SSOT: skills/references/task-tools-fallback.md. 아래 항목 각각에 대해 TaskCreate를 실행하세요.

Task 네이밍 규약: [Brainstorm] {항목명} (plan-task의 [Planning] Task와 구분) 완료 마킹 규약 [건너뛰기 금지]: 각 항목을 마치면 즉시 TaskUpdate(status="completed"), 마지막 항목(plan-task invoke)은 invoke 직전에 마킹 (규율 SSOT: rules/definition-of-done.md#task-마감-규율). work_id metadata: brainstorming 단계에서는 Work ID가 없으므로 {"phase": "brainstorming"}만 사용

  1. 프로젝트 컨텍스트 파악 (파일, 최근 커밋, docs)
  2. 명확화 질문 (한 번에 하나씩)
  3. 2-3가지 접근법 + 추천
  4. 설계 제시 및 사용자 승인
  5. 스펙 문서 작성 (docs/specs/YYYY-MM-DD-{topic}.md)
  6. 스펙 자가 검토 (플레이스홀더, 모순, 모호성)
  7. 사용자 스펙 검토 대기
  8. plan-task invoke

프로세스

1단계: 컨텍스트 파악

  • 관련 파일, README, 최근 커밋 확인
  • 규모 판단: 복수의 독립 서브시스템이면 분해 먼저 제안

2단계: 명확화 질문

  • 한 번에 하나의 질문만
  • 목적, 제약, 성공 기준에 집중
  • 가능하면 객관식 선택지 제공

3단계: 접근법 제안

  • 2-3가지 접근법과 트레이드오프
  • 추천안과 이유를 먼저 제시

4단계: 설계 제시

  • 각 섹션을 순서대로 제시하고 승인 확인
  • 아키텍처, 컴포넌트, 데이터 흐름, 에러 처리, 테스트 전략 포함
  • 수정 요청 시 해당 섹션 재작성

5단계: 스펙 문서 작성

저장 경로: docs/specs/YYYY-MM-DD-{topic}.md (docs/works/ 있으면 해당 Work와 연결)

스펙 문서 구조:

# {Topic} 설계

**Goal:** [한 문장]
**Architecture:** [2-3 문장]

## 요구사항
## 접근 방식
## 컴포넌트 구조
## 데이터 흐름
## 에러 처리
## 테스트 전략
## 범위 외

6단계: 자가 검토

  1. 플레이스홀더 스캔: TBD, TODO, 미완성 섹션 → 즉시 수정
  2. 일관성: 섹션 간 모순 없는지 확인
  3. 범위: 단일 plan으로 구현 가능한가?
  4. 모호성: 두 가지로 해석 가능한 요구사항 → 명확화

7단계: 사용자 검토 대기

세션 경계 주의: 이 단계에서 세션이 끝나면 대기 태스크가 다음 세션에 잔존한다 — 정상이다. 재개 판단 기준은 docs/specs/의 스펙 파일 (rules/task-resume.md 참고).

스펙을 `{path}`에 저장했습니다. 검토 후 수정 사항이 있으면 말씀해 주세요.
승인되면 plan-task로 넘어갑니다.

수정 요청 시 → 수정 후 자가 검토 재실행 승인 시 → 8단계

Read the full file on GitHub · 110 lines

Changes

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.

  1. 2d ago First seen · 110 lines · 43 tokens per session scan A 119c35a9277b

Subscribe to this mod's changes

brainstorming is a skill published in the GitHub repository This-HW/claude-code-kit (4 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,059 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

watch

File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…

SethGammon/Citadel · 70 tokens

pr-watch

Local PR watcher. Monitors CI status, automatically fixes failing checks by reading failure logs and applying targeted fixes, then optionally merges when all checks pass. Local CLI analog to Claude Code's cloud auto-fix feature.

SethGammon/Citadel · 46 tokens

qa

Browser-based QA verification. Launches a real browser, navigates the app, clicks buttons, fills forms, and tests user flows. Works as a standalone skill or as a phase end condition in campaigns. Requires Playwright (optional dependency, graceful skip if not installed).

SethGammon/Citadel · 56 tokens

review

5-pass structured code review — correctness, security, performance, readability, consistency.

SethGammon/Citadel · 17 tokens

live-preview

Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.

SethGammon/Citadel · 40 tokens

marshal

Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.

SethGammon/Citadel · 56 tokens