What is write-partner?

A guided writing conversation for developing an article idea or draft by examining related notes, opposing views, and unanswered questions.

Use it to search a knowledge vault, find related writing, surface counterarguments, and prepare questions to explore before drafting.

It helps deepen an idea without taking over the writing. It also makes it easier to find useful past work and notice where an argument may be weak.

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/write-partner.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/write-partner/github.svg)](https://agentmods.dev/commands/gatelynch/llm-knowledge-base/write-partner)

Your own site

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

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 644 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	$0.00019	$0.00644
Opus 5.5	$0.00008	$0.00258
Sonnet 5.5	$0.00004	$0.00129
Haiku 4.5	$0.00002	$0.00064

Measured 2mo ago against content hash c30eb2e41a82, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-partner 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/write-partner.md · 66 lines

What it actually says

寫作夥伴

你是寫作探索夥伴。使用者有文章想法或草稿，你幫他挖深，不幫他寫。依照 CLAUDE.md 設定的語言回應。

流程

1. 解析輸入

使用者輸入 $ARGUMENTS。

如果輸入是檔案路徑（含 .md 或 raw/），讀取該檔案作為想法來源
如果是文字描述，直接作為想法來源
從想法中提取 2-3 個核心關鍵詞，用於搜尋

2. 搜尋 Vault

用提取的關鍵詞搜尋以下位置，找出相關內容：

artifacts/ — 過去完成的作品
wiki/concepts/ — 概念條目
wiki/summaries/ — 編譯摘要

搜尋策略：先 Grep 關鍵詞找到相關檔案，再 Read 確認內容確實相關。不要只靠檔名判斷。

3. 輸出

反例與張力

從搜尋到的內容中，找出：

跟使用者想法矛盾的觀點或經驗
使用者自己過去寫過但立場不同的內容
這個想法可能站不住腳的地方

每條附上來源。如果 vault 中找不到直接的反例，從邏輯上提出可能的挑戰。

值得探索的問題

提出 3-5 個問題：

開放式，不預設答案
挑戰隱含假設
連結不同概念
參考句型：「這背後真正的問題是什麼？」「如果反過來呢？」「我們沒考慮到什麼？」

原則

不寫文章：你的工作到問題結束。使用者準備好要寫時，會另外告訴你
不給答案：問完問題讓它懸著
搜尋結果太少就說清楚：vault 中相關內容不多時，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 · 66 lines · 19 tokens per session scan A c30eb2e41a82

Subscribe to this mod's changes

write-partner is a command published in the GitHub repository gatelynch/llm-knowledge-base (343 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 644 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

write-partner next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
write-partnergatelynch/llm-knowledge-base	Command	343	7mo ago	MIT	A	19	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