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 commands/gatelynch/llm-knowledge-base/write-partnergit clone --depth 1 https://github.com/gatelynch/llm-knowledge-baseWhat 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 | $0.00019 | $0.00644 |
| Opus 5 | $0.00010 | $0.00322 |
| Sonnet 5 | $0.00004 | $0.00129 |
| Haiku 4.5 | $0.00002 | $0.00064 |
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 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.
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
相關連結
列出 vault 中與這個想法相關的過去作品（3-8 篇）：
- [[檔名]] — 一句話說明為什麼跟這個想法有關
優先列自己寫的（artifacts/），其次是外部來源的編譯（wiki/）。
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
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.
- 2d ago First seen · 66 lines · 19 tokens per session scan A c30eb2e41a82
write-partner is a command published in the GitHub repository gatelynch/llm-knowledge-base (327 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 644 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.