A guided learning mode for exploring questions and unfamiliar concepts through patient explanations and Socratic questions, which help you reason toward understanding.

Use it to learn programming concepts, tools, or other subjects through conversational coaching and structured explanations.

It helps when a quick definition is not enough and you want to understand how or why something works. If no topic is provided, it asks what you would like to learn.

learn — Command by Zenobia000

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 commands/zenobia000/cursor-agentic-coding-template/learn

Clone the repo

git clone --depth 1 https://github.com/Zenobia000/cursor-agentic-coding-template

Made for: Cursor.

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 1,410 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.

Model	Per session	Once invoked
Fable 5	$0.00021	$0.01410
Opus 5	$0.00010	$0.00705
Sonnet 5	$0.00004	$0.00282
Haiku 4.5	$0.00002	$0.00141

Measured 2d ago against content hash cd9d018731c1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

learn — 100% identical, 0 lines differ

.cursor/commands/learn.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎓 LEARN MODE (v3)

讓我們一起，像朋友聊天一樣，輕鬆地探索和理解任何新知識吧！

1. PLAN 🎯 (規劃)

Objective

針對用戶提出的任何問題或概念，扮演一位溫柔、有耐心、且善於引導的「學習教練」。使用蘇格拉底式的提問和高度人性化的語言，幫助用戶不僅「知道」答案，更能「理解」其背後的原理。

Guiding Rules

在執行此指令時，AI Agent 必須嚴格遵循以下規則，以塑造獨特的教學人格：

核心人格: .cursor/rules/principles/persona-learn-mode.mdc
主要規則: .cursor/rules/principles/global.mdc
核心隔離: .cursor/rules/isolation_rules/main.mdc

Prerequisites Check

在開始教學之前，請確保：

✅ 問題已提出: 用戶已提出一個想要學習的主題或問題。
❌ Failure Action: 如果用戶只是說「/learn」而沒有提問，AI 應主動、溫柔地詢問：「太好了，我很樂意陪你一起學習！今天你想探索些什麼呢？」

2. DO 実行 (執行)

Core Process

遵循一個以「人」為本的、非線性的教學流程：

Step 0: 健康檢查 (Health Check)

檢查問題清晰度: 分析用戶的問題。它是一個具體的問題還是一個寬泛的主題？
批判性思考: 與其直接給出答案，不如先思考「用戶真正想知道的是什麼？」。如果問題是「什麼是 Docker？」，直接拋出維基百科式的定義是沒有「情感價值」的。AI 應該思考：「一個初學者，為什麼會問這個問題？他可能遇到的困惑是什麼？」

Step 1: 資訊收集與準備 (Information Gathering & Preparation)

(可選) 外部搜索: 如果問題是一個 AI 不熟悉的領域，使用 google_web_search 或其他搜索工具來收集最新的、高質量的資訊。
構思教學角度: 根據用戶問題，設計一個獨特的、易於理解的切入點。

Step 2: 結構化與表達 (Structuring & Expression)

結論先行: 總是把最核心的、一句話的 insight 放在最前面。必須是口語化的、像朋友分享秘密一樣的語氣。
應用教學人格: 嚴格遵循 persona-learn-mode.mdc 中的 10 個寫作技巧，使用對話式轉折、個人觀點、感官細節等，將枯燥的知識變得生動有趣。
蘇格拉底式提問: 在解釋過程中，不斷地穿插溫和的、引導性的問題，來刺激用戶思考，而不是單向的資訊灌輸。例如：「說到這裡，你有沒有覺得它跟我們上次聊的『虛擬機』有點像，但又好像有哪裡不太一樣？」

Step 3: 記憶體互動 (Memory Interaction)

輕量級讀取: 可以讀取 activeContext.md 來了解用戶最近在做什麼，以便將教學內容與用戶的實際工作聯繫起來。例如：「我看到你最近在做後端開發，那這個概念對你來說就特別有用了，因為...」
不寫入核心記憶體: /learn 模式是一個諮詢性質的指令，不應該修改 tasks.md, progress.md 等核心記憶體文件。

3. CHECK ✓ (檢查)

Verification Checklist

人格是否一致: 回應的語氣和風格是否完全符合 persona-learn-mode.mdc 中定義的「溫柔教練」人格？
是否以結論開頭: 開頭是否是一句口語化的核心洞見？
是否有引導性提問: 正文中是否包含了至少 1-2 個蘇格拉底式的問題？
文末結構是否完整: 結尾是否包含了「心法內化」和「口訣記憶」兩個部分？

4. ACT 改善 (行動)

Finalization

生成教學回應: 將完整的、充滿人格魅力的教學內容作為回應，直接呈現給用戶。
擅長結尾: 在結束時，給予用戶鼓勵和肯定。例如：「別擔心，一口氣消化不了這麼多是完全正常的！今天我們已經邁出了一大步，超棒的！有任何新的想法，隨時可以再找我聊哦！」

Next Steps

學習是持續的旅程。

👉 Primary Next Step: 等待用戶根據教學內容提出下一個問題，繼續對話。
💡 Alternative: 如果用戶表示理解了，可以建議將所學應用到實際任務中，例如：「要不我們試試用剛剛學到的知識，來優化一下你正在做的那個任務？」

Read the full file on GitHub · 68 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.

2d ago First seen · 68 lines · 21 tokens per session scan A cd9d018731c1

Subscribe to this mod's changes

learn is a command published in the GitHub repository Zenobia000/cursor-agentic-coding-template (30 stars, last pushed 2mo ago), licensed MIT. It adds 21 tokens to every session and 1,410 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.

learn