summarize

A skill that fetches a specific web page and saves a structured summary as a note in the vault's resources folder. It is intended for a URL the user wants read in depth or summarized.

In plain words
What is it for?
Use it to summarize articles, documentation, papers, videos, or other pages when the user provides a URL and asks for notes or a deep read.
Why use it?
It preserves the important points from a web page in a searchable, organized note.

Skill for Claude CodeCodex

Part of the onebrain plugin — 32 skills, 5 agents, 2 hooks shipped together

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 skills/onebrain-ai/onebrain/summarize
Any agent
npx skills add onebrain-ai/onebrain --skill summarize
Clone the repo
git clone --depth 1 https://github.com/onebrain-ai/onebrain

Made for: Claude Code, Codex.

Or install onebrain, the plugin that ships this one along with the rest of its 32 skills, 5 agents, 2 hooks.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,306 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.

ModelPer sessionOnce invoked
Fable 5 $0.00078 $0.01306
Opus 5 $0.00039 $0.00653
Sonnet 5 $0.00016 $0.00261
Haiku 4.5 $0.00008 $0.00131

Measured 3d ago against content hash 76447a173e20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summarize 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 3d 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.

.claude/plugins/onebrain/skills/summarize/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Summarize

Fetch a URL and create a structured summary note in your resources folder.

Usage: /summarize [url]


Step 1: Get the URL

If provided after the command, use it directly.

If not, ask:

What URL do you want to summarize?


Step 2: Check Bookmarks

Grep [resources_folder]/Bookmarks.md for the URL. If found, note it silently : you will offer to remove it after the summary note is saved (Step 7).


Step 3: Ask for Context

Optional but helpful : ask:

Why are you saving this? (e.g., research for a project, reference for later, interesting read)

This context shapes how the summary is framed.


Step 4: Fetch and Read

Fetch the URL content. If it fails:

I couldn't fetch that URL. You can paste the content directly and I'll summarize it.

Read the full page content.


Step 5: Extract Key Information

Identify:

  • Title of the article/page
  • Author and publication date (if available)
  • Core thesis or main point
  • Key arguments or findings (3-7 points)
  • Memorable quotes (1-3 if applicable)
  • Actionable takeaways (if any)
  • Content type: article, documentation, paper, blog post, video transcript, etc.

Step 6: Choose Subfolder and Save

Resolve subfolder:

  1. Glob existing subfolders in [resources_folder]/*/
  2. Suggest a kebab-case subfolder based on the article's topic (max 2 levels, e.g. productivity/tools)
  3. Present to user: "I'd file this under [resources_folder]/[suggested-path]/. OK?"
  4. Use confirmed path for file creation.

Create the summary note at [resources_folder]/[subfolder]/[Article Title].md:

---
tags: [summary, topic-tag]
created: YYYY-MM-DD
source: /summarize
url: [URL]
author: [Author Name]
published: [Publication date if known]
---

# [Article Title]

> **Source:** [URL]
> **Saved:** YYYY-MM-DD
> **Why I saved this:** [User's context, if provided]

## Summary

[2-3 sentence summary of the main point]

## Key Points

- [Point 1]
- [Point 2]
- [Point 3]

## Notable Quotes

> "[Quote]"
> : [Author/Source]

## My Takeaways

[Leave blank for the user to fill in, or ask if they want to add any now]

## Related

[[Link to related vault notes]]

Read the full file on GitHub · 169 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.

  1. 3d ago First seen · 169 lines · 78 tokens per session scan A 76447a173e20

Subscribe to this mod's changes

summarize is a skill published in the GitHub repository onebrain-ai/onebrain (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 78 tokens to every session and 1,306 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.

Related

Other skills, from other repositories

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".

breferrari/obsidian-mind · 67 tokens

mermaid-visualizer

Transform text content into professional Mermaid diagrams for presentations and documentation. Use when users ask to visualize concepts, create flowcharts, or make diagrams from text. Supports process flows, system architectures, comparisons, mindmaps, and more with built-in syntax error prevention.

breferrari/obsidian-mind · 57 tokens

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…

breferrari/obsidian-mind · 142 tokens

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…

breferrari/obsidian-mind · 102 tokens

llm-wiki

Build and maintain a persistent, interlinked Obsidian-compatible markdown wiki using Karpathy's LLM Wiki pattern. Extension-backed with auto-generated metadata, guardrails, and 14 custom tools (+3 opt-in agent-trajectory tools).

zosmaai/pi-llm-wiki · 52 tokens

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.

917Dhj/DeepPaperNote · 71 tokens