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 kopp0510/claude-dd --skill design-brainstormgit clone --depth 1 https://github.com/kopp0510/claude-ddWrote 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/kopp0510/claude-dd/design-brainstorm)<a href="https://agentmods.dev/skills/kopp0510/claude-dd/design-brainstorm"><img src="https://agentmods.dev/badge/skills/kopp0510/claude-dd/design-brainstorm/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/kopp0510/claude-dd/design-brainstorm"><img src="https://agentmods.dev/badge/skills/kopp0510/claude-dd/design-brainstorm.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00083 | $0.01093 |
| Opus 5 | $0.00042 | $0.00547 |
| Sonnet 5 | $0.00017 | $0.00219 |
| Haiku 4.5 | $0.00008 | $0.00109 |
Grade A, and why
design-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.
What it actually says
Design Brainstorm — 蘇格拉底式設計對話
借鑑 obra/superpowers 的 brainstorming 概念；提問紀律借鑑 mattpocock/skills 的 grilling。
硬閘門
設計未批准前，不寫任何程式碼 — 不呼叫實作技能、不建專案骨架，直到設計呈現且使用者批准。
啟動時調用 EnterPlanMode，設計完成後 ExitPlanMode 讓使用者審閱。
工作流程
1. 探索專案脈絡
讀 CLAUDE.md、README.md、相關目錄結構與最近 git 提交，識別既有模式與技術棧，
確保設計建議符合專案現況。
2. 提問釐清
一次只問一個問題，偏好多選題，每題都要推進理解。 提問順序：目標 → 使用者 → 限制 → MVP 範圍。
事實自己查，決策才問人：
- 能從環境查到的「事實」自己查（filesystem、程式碼、git、設定檔）
- 「決策」才逐一放到使用者面前，且每題附上自己的建議答案
- 判斷基準：有標準答案 → 事實，去查；取決於偏好/取捨 → 決策，去問
3. 範圍評估
小型（<1 天）直接設計；中型（1–3 天）分階段；大型（>3 天）先拆成獨立子專案， 各自 brainstorm。
4. 提出 2–3 個方案
每案含：核心思路一句話、優缺點、技術選擇、預估複雜度、適合場景。
YAGNI：每案都是最小可行方案。「以後可能需要」的功能 → 移除， 只確保設計之後容易加入。質疑每個非必要功能：「沒有這個會怎樣？」
5. 分段呈現設計
依序呈現並逐段確認：資料模型 → API 設計 → 核心邏輯 → UI/UX 流程（如適用）→ 錯誤處理。 每段問「這部分同意嗎？要調整什麼？」
若涉及 UI/架構圖，以獨立訊息提議產出視覺輔助（Mermaid 圖 / UI mockup），同意後再做。
6. 寫設計文件
寫入 docs/designs/YYYY-MM-DD-<topic>-design.md，結構：問題描述、設計決策（含理由）、
技術設計（資料模型 / API / 核心邏輯）、範圍排除（明確不做的事）、開放問題。
7. 自我審查
檢查：無佔位符或 TODO、無內部矛盾、無模糊描述、技術選擇皆有理由、範圍排除清楚、 無 YAGNI 功能。
8. 使用者審查 → 下一步
依回饋修改至批准。批准後的下一步：交 task-planner 拆微任務，或直接進
8 步開發迴圈實作。批准前後都不跳過迴圈的測試與 review 步驟。
常見錯誤
| 錯誤 | 正確做法 |
|---|---|
| 設計前就開始寫程式碼 | 堅守硬閘門 |
| 一次問太多問題 | 一次一個，多選優先 |
| 把查得到的事實拿去問使用者 | 事實自己查，只問決策並附建議答案 |
| 假設使用者的技術偏好 | 提供選項讓使用者選 |
| 設計過度 | YAGNI — 只做需要的 |
| 跳過範圍評估 | 大專案必先拆分 |
| 設計文件有佔位符 | 自我審查消除所有 TODO |
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 Changed 309d5ea08b88
- 9d ago First seen · 78 lines · 83 tokens per session scan A dbc9cafc646f
design-brainstorm is a skill published in the GitHub repository kopp0510/claude-dd (6 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 1,093 once invoked, about $0.0004 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
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".