awesome-second-brain: Command for Claude Code

.claude/commands/core/ingest-url.md

ingest-url is a command for Claude Code from superuser-pal/awesome-second-brain. It costs 39 tokens per session (650 once invoked), scanned A, original, MIT.

A command that captures a web page from a URL, converts it to clean Markdown text, and saves it in a vault for processing. The vault is a structured collection of stored notes.

In plain words
What is it for?
Saving articles, documentation, and other web pages as dated notes, then assigning them to a relevant subject area and folder.
Why use it?
Copying web content, classifying it, and filing it manually takes several steps. This combines extraction, staging, classification, and routing into one workflow.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is superuser-pal/awesome-second-brain's own configuration. It tells Claude Code how to work on awesome-second-brain itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything awesome-second-brain configures →

Reuse

Borrowing it

Nothing to install: this file belongs to superuser-pal/awesome-second-brain. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/superuser-pal/awesome-second-brain/main/.claude/commands/core/ingest-url.md
Clone the repo
git clone --depth 1 https://github.com/superuser-pal/awesome-second-brain

Made for: Claude Code.

Wrote 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.

agentmods badge for ingest-url

README.md
[![agentmods](https://agentmods.dev/badge/commands/superuser-pal/awesome-second-brain/ingest-url.svg)](https://agentmods.dev/commands/superuser-pal/awesome-second-brain/ingest-url)
Your own site
<a href="https://agentmods.dev/commands/superuser-pal/awesome-second-brain/ingest-url"><img src="https://agentmods.dev/badge/commands/superuser-pal/awesome-second-brain/ingest-url.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 650 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00039 $0.00650
Opus 5 $0.00019 $0.00325
Sonnet 5 $0.00008 $0.00130
Haiku 4.5 $0.00004 $0.00065

Measured 7d ago against content hash 6812d6f870ff, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

ingest-url 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 7d 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/commands/core/ingest-url.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ingest URL

Extract a web page as clean markdown and route it directly to the vault in one step.

Usage

/ingest-url <url>

Workflow

1. Preflight Check

Verify defuddle CLI is installed:

defuddle --version

If not installed, fail gracefully:

⚠️  defuddle CLI not found.

Install it with:
  npm install -g defuddle-cli

Then re-run: /ingest-url <url>

Stop here — do not continue without defuddle.

2. Extract Content with Defuddle

defuddle parse <url> --md

Capture the markdown output. If defuddle returns an error or empty output:

⚠️  defuddle could not extract content from <url>.
Try opening the URL in a browser to confirm it's accessible.

Stop here if extraction fails.

3. Stage as Raw Note

Save the extracted markdown to inbox/raw/ using the standard InboxRaw schema:

---
date: YYYY-MM-DD
created: YYYY-MM-DD
status: unprocessed
---

# [Page title from defuddle output]

> Source: <url>

[Extracted markdown content]

Filename: [slugified-title]-[YYYY-MM-DD].md

4. Process

Run /process on the staged note to:

  • Assign domain from content analysis
  • Assign type (expect source for most URL ingests, but allow content analysis to override)
  • Complete frontmatter (name, description, tags, origin: url)
  • Move from inbox/raw/inbox/ready/

5. Distribute

Run /distribute on the processed note to:

  • Route to domains/[domain]/02_PAGES/ (or 02_PAGES/sources/ if the sources/ sub-folder exists)
  • Apply steps 3b and 3c from the distribute workflow (type assignment + sub-folder routing)
  • Present routing plan and wait for confirmation

6. Report

✓ Ingested: <url>
  Extracted: [Page title]
  Domain: [domain]
  Type: source
  Destination: domains/[domain]/02_PAGES/[sub-folder/][filename]

Notes

  • This command chains three existing operations — no new logic beyond the chain itself.
  • /process and /distribute retain their normal confirmation prompts; this command does not bypass them.
  • If the URL content is clearly not a source (e.g., a decision log or report), /process may assign a different type — that is correct behavior.
  • See [[.claude/skills/defuddle/SKILL|defuddle skill]] for defuddle CLI details.

Read the full file on GitHub · 104 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. 7d ago First seen · 104 lines · 39 tokens per session scan A 6812d6f870ff

Subscribe to this mod's changes

ingest-url is a command published in the GitHub repository superuser-pal/awesome-second-brain (14 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 650 once invoked, about $0.0002 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.