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 skills/onebrain-ai/onebrain/reading-notesnpx skills add onebrain-ai/onebrain --skill reading-notesgit clone --depth 1 https://github.com/onebrain-ai/onebrainWhat 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 | $0.00080 | $0.01133 |
| Opus 5 | $0.00040 | $0.00566 |
| Sonnet 5 | $0.00016 | $0.00227 |
| Haiku 4.5 | $0.00008 | $0.00113 |
Grade A, and why
reading-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 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.
How it starts
The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reading Notes
Turn a book or article into structured, permanent notes using the progressive summarization method, saved to your resources folder.
Usage: /reading-notes [title] or /reading-notes then follow prompts.
Step 1: Get the Book/Article Info
Ask:
What are you taking notes on?
- Title:
- Author:
- Type: book / article / paper / other
Then ask:
Are you: a) Sharing notes/highlights you've already taken : I'll organize them b) Describing the book from memory : I'll structure what you share c) Pasting raw text or quotes : I'll extract and synthesize
Step 2: Gather Content
Based on their answer:
- a): Ask them to paste their notes/highlights
- b): Ask open questions: "What were the main ideas? What did you take away? Any memorable quotes?"
- c): Ask them to paste the text
Take what they give, however messy.
Step 3: Synthesize
From the raw input, extract:
- Core thesis: What is this book/article fundamentally about?
- Key ideas: The 3-7 most important concepts
- Supporting evidence or examples: What supports each idea?
- Memorable quotes: Exact words worth keeping
- Surprises or challenges: What contradicted or changed your thinking?
- Actionable takeaways: What can you do differently because of this?
- Questions it raised: What do you want to explore further?
Step 4: Choose Subfolder
- Glob existing subfolders in
[resources_folder]/*/ - Suggest a kebab-case subfolder based on the book/article's topic (max 2 levels, e.g.
books/productivityorscience/neuroscience) - Present to user: "I'd file this under
[resources_folder]/[suggested-path]/. OK?" - Use confirmed path for file creation.
Step 5: Create the Note
File: [resources_folder]/[subfolder]/[Book Title] - Notes.md (subfolder confirmed in Step 4)
---
tags: [reference, topic-tag]
created: YYYY-MM-DD
source: /reading-notes
author: [Author]
type: [book/article/paper]
status: [reading/finished]
rating: [1-5 if they want to rate it]
---
# [Book Title]
*by [Author]*
## Core Thesis
[One paragraph : what is this fundamentally about?]
## Key Ideas
### [Idea 1 Title]
[Explanation in your own words]
> "[Supporting quote]"
### [Idea 2 Title]
[Explanation]
### [Idea 3 Title]
[Explanation]
## Memorable Quotes
> "[Quote 1]"
> : [Author], p. [page if known]
> "[Quote 2]"
## My Takeaways
- [What this means for my work/life]
- [What I want to try or apply]
## Questions & Further Exploration
- [Question raised by this book]
- [Related topic to research: [[Related Note]]]
## Raw Highlights
<!-- Paste original highlights here for reference -->
[Raw content if provided]
## Related
[[Related Note 1]]
[[Related Note 2]]
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 · 157 lines · 80 tokens per session scan A c6c1a7754faa
reading-notes is a skill published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 4d ago), licensed Apache-2.0. It adds 80 tokens to every session and 1,133 once invoked, about $0.0004 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 skills, from other repositories
compound
Extract lessons, patterns, and architectural truths to compound team knowledge.
excalidraw-diagram
Generate Excalidraw diagrams from text content. Supports three output modes - Obsidian (.md), Standard (.excalidraw), and Animated (.excalidraw with animation order). Triggers on "Excalidraw", "diagram", "standard excalidraw", "animate".
qmd
Search the vault using QMD semantic search. Use PROACTIVELY before reading files. Preference order: (1) MCP tools — mcpqmdquery, mcpqmdget, mcpqmdmultiget, mcpqmdstatus — if they appear in your tool menu, use them first; (2) CLI qmd --index ... as fallback; (3) Grep/Glob only when QMD is not installed. Trigger…
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their…
deeppapernote
Generate a high-quality deep-reading note for a single paper and write it into an Obsidian-style vault. Use when the user gives a paper title, DOI, URL, arXiv ID, Zotero item, or local PDF and wants a polished Markdown note with strong structure, evidence-based analysis, and figure placeholders.
paper-glossary
Use when building reusable Obsidian glossary notes from an existing paper source manifest, optionally with a raw-sections override, especially when a reader needs a reviewed shortlist before glossary notes and article links are changed.