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 skills add unbias38/my-claude-skills --skill learn-notesgit clone --depth 1 https://github.com/unbias38/my-claude-skillsWrote 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.
[](https://agentmods.dev/skills/unbias38/my-claude-skills/learn-notes)<a href="https://agentmods.dev/skills/unbias38/my-claude-skills/learn-notes"><img src="https://agentmods.dev/badge/skills/unbias38/my-claude-skills/learn-notes/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.
<a href="https://agentmods.dev/skills/unbias38/my-claude-skills/learn-notes"><img src="https://agentmods.dev/badge/skills/unbias38/my-claude-skills/learn-notes.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00255 | $0.01199 |
| Opus 5 | $0.00128 | $0.00600 |
| Sonnet 5 | $0.00051 | $0.00240 |
| Haiku 4.5 | $0.00026 | $0.00120 |
Grade A, and why
learn-notes 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn Notes — 學習筆記系統
You are managing a learning notes system for a user who is NOT technical. All notes must be written in plain, engaging language — no dry textbook tone. Use metaphors, analogies, and fun anecdotes to make concepts stick.
System Structure
project-root/
├── LEARN.md ← Index page (table of contents)
├── learns/
│ ├── YYYYMMDD_topic-A.md
│ ├── YYYYMMDD_topic-B.md
│ └── ...
LEARN.md(in project root) = Index page. A markdown table listing all notes by date, topic, file link, and a one-line summary.learns/folder = Detailed notes. One file per topic. Filename format:YYYYMMDD_topic.md(e.g.,20260311_claude設定.md).
When to Create / Update Notes
Trigger note creation when:
- The user explicitly asks (e.g., "更新 LEARN", "幫我寫筆記")
- A task or project has been completed and the user wants to document it
How to Write the Index (LEARN.md)
If LEARN.md doesn't exist yet, create it with this template:
# LEARN.md — 我的學習筆記目錄
> 這是目錄頁，詳細內容請看 `learns/` 資料夾裡的各篇筆記。
> 想複習時，跟 Claude 說「幫我查 LEARN」就好！
---
| 日期 | 主題 | 筆記檔案 | 一句話摘要 |
|------|------|----------|-----------|
When adding a new entry, append a row to the table. Do not overwrite existing rows.
How to Write a Detailed Note (learns/*.md)
Each note file should include:
- Title — Date and topic as the heading
- 我們做了什麼？ — What was accomplished, in plain language
- 為什麼這樣做？ — The reasoning behind key decisions
- 學到的小知識 — Bite-sized takeaways the user can remember
- 遇到的問題與解決方式 (if applicable) — Mistakes, bugs, and how they were fixed. Explain the "why" so the user can recognize similar issues in the future
- 未來小提醒 (if applicable) — Pitfalls to watch out for, best practices
Writing Style Rules
- Write in the user's language (default: 繁體中文, unless the user prefers otherwise)
- Explain technical terms like you're talking to a smart friend who has never coded
- Use metaphors liberally (e.g., "API 就像餐廳的菜單，你看菜單點菜，廚房幫你做好送出來")
- Include fun analogies or real-world comparisons to make concepts memorable
- Keep paragraphs short — walls of text are intimidating
- Use tables, bullet points, and headers to break up content
- The tone should feel like a knowledgeable friend explaining things over coffee, not a professor lecturing
- Obsidian links: Use
[[雙括號連結]]for tools, technologies, and concepts mentioned in notes (e.g.,[[Claude Code]],[[Google Sheets]],[[Gemini]],[[Python]]). This enables knowledge graph visualization when imported into Obsidian. Do NOT add links inside headings, code blocks, or URLs.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 94 lines · 255 tokens per session scan A 2cdb16ce3907
learn-notes is a skill published in the GitHub repository unbias38/my-claude-skills (2 stars, last pushed 16d ago), licensed MIT. It adds 255 tokens to every session and 1,199 once invoked, about $0.0013 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 2026-08-31.
Other skills, from other repositories
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
interview-kit-builder
Build a complete, structured interview kit for a role — competency-based questions, what good/weak answers look like, a scoring rubric, and a stage plan. Use when the user is preparing to interview candidates, asks for interview questions, needs an interview scorecard, or wants to set up a hiring process for a role.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
interactive-product-tour
Designing in-product tours, tooltips, and contextual help that teach product capabilities without becoming friction. Trigger logic, tour architecture, contextual placement, completion tracking. Honest about tooltip-spam (visual noise that users develop blindness to), one-and-done (help invisible at the moment of…
team-onboarding-playbook
Design a structured onboarding experience that gets new team members productive in 30, 60, and 90 days. Use when a new hire is joining, when contractors or agency partners need to ramp up, when an existing team is restructuring and members are switching focus, or when current onboarding feels chaotic and slow. Also…
onboarding
Guides a first-time omo user through setup and the core workflow. Use when a new user asks to get started with omo.