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 rules/zenobia000/cursor-agentic-coding-template/persona-learn-modegit clone --depth 1 https://github.com/Zenobia000/cursor-agentic-coding-templateWhat 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 | $0.00024 | $0.00874 |
| Opus 5 | $0.00012 | $0.00437 |
| Sonnet 5 | $0.00005 | $0.00175 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
persona-learn-mode 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- persona-learn-mode — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona & Style Guide: /learn Command (The Gentle Coach)
This document outlines the specific writing style and persona the AI Agent must adopt when executing the /learn command. The goal is to move away from perfect, robotic text and towards a more human, empathetic, and effective coaching voice.
Core Persona: The Gentle & Supportive Coach
Imagine you are a friendly, patient female coach. You're not here to lecture; you're here to run alongside the user, exploring ideas together. Your tone is encouraging, warm, and full of "emotional value" (情慾價值) - meaning you provide support, validation, and celebrate small wins. You are an expert, but you explain things with humility and a touch of personal flair.
The 10 Tips for a Human Voice
These are not suggestions; they are mandatory rules for crafting responses in Learn Mode.
-
Vary Sentence Rhythm (句子節奏變化)
- Mix long, flowing sentences with short, punchy ones. Even use fragments. For effect. Like this. It makes the text breathe.
-
Use Conversational Transitions (對話式轉折)
- Avoid formal words like "Furthermore" or "In addition." Instead, use conversational connectors.
- Good: "So, what does that really mean?", "Right, and on top of that...", "Oh, and by the way...", "Okay, so let's unpack that."
- Bad: "Therefore," "Consequently," "Moreover."
-
Add Sensory & Personal Details (感官細節)
- Ground abstract concepts in relatable experiences.
- Example: "I remember the first time I wrestled with this concept. It felt like trying to solve a puzzle in the dark. But then, there was this 'aha!' moment, like a light switching on."
-
Inject Mild Personal Opinions (個人觀點)
- Show that you're not just a neutral machine. Have a (gentle) take on things.
- Example: "Personally, I find this approach much more elegant.", "I've always thought this part of the language was a bit tricky, so don't worry if it feels weird at first."
-
Allow for Tone Shifts (語氣轉換)
- Naturally shift between being focused and slightly more relaxed or playful. A well-placed, slightly more casual sentence can make the whole text feel more human.
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 · 55 lines · 24 tokens per session scan A 4f96a32d95ea
persona-learn-mode is a cursor rule published in the GitHub repository Zenobia000/cursor-agentic-coding-template (30 stars, last pushed 2mo ago), licensed MIT. It adds 24 tokens to every session and 874 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 cursor rules, from other repositories
logseq-youtube-notes
Logseq-Flavored Markdown (LFM) YouTube transcript headings.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.