A command for saving ideas from a conversation as organized notes or an article outline in a brainstorming folder.

Use it to create a discussion record, an article draft outline, or both, with links to relevant notes from the knowledge vault.

It preserves useful conclusions, evidence, uncertainties, and the difference between the user's ideas and the assistant's suggestions. It also waits for the user's choice before recording the conversation.

How gatelynch/llm-knowledge-base configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gatelynch/llm-knowledge-base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/gatelynch/llm-knowledge-base/main/.claude/commands/braindump.md

Clone the repo

git clone --depth 1 https://github.com/gatelynch/llm-knowledge-base

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/gatelynch/llm-knowledge-base/braindump/github.svg)](https://agentmods.dev/commands/gatelynch/llm-knowledge-base/braindump)

Your own site

<a href="https://agentmods.dev/commands/gatelynch/llm-knowledge-base/braindump"><img src="https://agentmods.dev/badge/commands/gatelynch/llm-knowledge-base/braindump/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/gatelynch/llm-knowledge-base/braindump"><img src="https://agentmods.dev/badge/commands/gatelynch/llm-knowledge-base/braindump.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,067 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00021	$0.01067
Opus 5.5	$0.00008	$0.00427
Sonnet 5.5	$0.00004	$0.00213
Haiku 4.5	$0.00002	$0.00107

Measured 2mo ago against content hash 38d0eef3f351, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

braindump 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 2mo 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.

.claude/commands/braindump.md · 97 lines

What it actually says

對話沉澱

把這次對話中討論過的想法沉澱成素材，存到 brainstorming/chat/。依照 CLAUDE.md 設定的語言回應。

流程

1. 確認範圍

先問使用者（等對方回覆才繼續）：

你想要怎麼記錄這次對話？

問答沉澱 — 記錄討論過程、結論、還沒想清楚的部分

文章草稿 — 根據對話生成文章架構，經你同意後才寫

兩者都要（分別存成不同檔案）

2. 決定檔名

格式：brainstorming/chat/YYYYMMDD {主題}.md

如果使用者有提供 $ARGUMENTS，用它當主題
如果沒有，從對話內容中提取主題
問答沉澱和文章草稿用不同檔名，例如：
- 20260404 重新打造第二大腦問答沉澱.md
- 20260404 重新打造第二大腦文章草稿.md

3. 寫問答沉澱

如果使用者選了 1 或 3，按以下格式寫：

---
question: "這次對話的核心問題（一句話）"
asked_at: YYYY-MM-DD
sources: [[[相關的 vault 檔案]]]
---

內容結構

TL;DR：2-3 句話總結這次對話最重要的收穫
結論：對話中形成的洞見，分主題列出。每條要有具體內容，不是空泛的摘要
證據：
- 對話中挖出的反例與張力
- vault 中的佐證（附 [[連結]]）
- 使用者自己舉的具體例子
不確定性：還沒想清楚的問題、懸著的問題、有矛盾但還沒解決的地方

重要原則

區分「使用者自己說的」和「AI 提出的」——使用者的原話和立場要忠實保留
使用者說「還沒想清楚」的地方，就記「還沒想清楚」，不要幫他補答案
sources 只列對話中實際引用或搜尋過的 vault 檔案

4. 寫文章草稿

如果使用者選了 2 或 3：

4a. 先提出文章架構

根據對話內容，生成一個 3-5 段的文章架構，每段包含：

段落標題
1-2 句話說明這段要寫什麼

架構要遵循 CLAUDE.md 中定義的寫作風格。預設原則：

從真實故事出發 → 反轉 → 帶著疑惑反思 → 留下沒有答案的問題
不用「總結來說」收尾
問完問題不給答案

把架構給使用者看，等使用者同意或修改後才繼續寫。

4b. 寫草稿

使用者同意架構後，寫成完整文章草稿，存到 brainstorming/chat/。

草稿原則：

用對話中使用者自己的語言和例子，不要另外發明
使用者沒說過的故事不要編
對話中懸著的問題，在文章中也讓它懸著
這是草稿，放在 brainstorming/ 而非 artifacts/——使用者自己決定什麼時候搬到 artifacts/

原則

先問再做：不要假設使用者要哪種格式
文章架構一定要先給使用者看過：沒有同意不動手寫
不主動搬到 artifacts/：brainstorming/chat/ 是 AI 的，artifacts/ 是使用者自己的
素材不夠就說清楚：如果對話內容太短或太散，誠實說，不要硬湊

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.

2mo ago First seen · 97 lines · 21 tokens per session scan A 38d0eef3f351

Subscribe to this mod's changes

braindump is a command published in the GitHub repository gatelynch/llm-knowledge-base (343 stars, last pushed 7mo ago), licensed MIT. It adds 21 tokens to every session and 1,067 once invoked, about $0.0001 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 2026-08-30.

Writing and docs

braindump next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
braindumpgatelynch/llm-knowledge-base	Command	343	7mo ago	MIT	A	21	Claude Code
checklistgithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	yesterday	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	yesterday	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	yesterday	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	yesterday	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	yesterday	MIT	A	14	Claude Code

llm-knowledge-base: Command for Claude Code