A command for extracting structured information from a web page or local file and returning it as JSON or Markdown. You provide a source and, optionally, the fields or information you want to collect.

Use it to extract items such as people and job titles, pricing plans, API endpoints, or a sensible summary from a URL, local file, or PDF.

It turns unstructured page or document content into a consistent result without requiring a separate Python package. It also avoids inventing fields that are not present in the source.

extract — Command for coding agents by Achitokun14: A command for extracting structured information from a web…

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 commands/achitokun14/claude-universal/extract

Clone the repo

git clone --depth 1 https://github.com/Achitokun14/claude-universal

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/achitokun14/claude-universal/extract.svg)](https://agentmods.dev/commands/achitokun14/claude-universal/extract)

Your own site

<a href="https://agentmods.dev/commands/achitokun14/claude-universal/extract"><img src="https://agentmods.dev/badge/commands/achitokun14/claude-universal/extract.svg" alt="Measured on agentmods" height="20"></a>

Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 356 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.

Model	Per session	Once invoked
Fable 5	$0.00019	$0.00356
Opus 5	$0.00010	$0.00178
Sonnet 5	$0.00004	$0.00071
Haiku 4.5	$0.00002	$0.00036

Measured 4d ago against content hash 886bf78efb09, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

extract 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 4d 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.

user/commands/extract.md · 42 lines

What it actually says

Extract structured data from a source using Claude itself (no Python dep required).

Steps:

Parse $ARGUMENTS:
- First token = source (URL or local file path).
- Rest = free-text schema hint (e.g. "people and their titles", "pricing tiers", "API endpoints").
- If missing source: ask "What should I extract from (URL or path)?".
Fetch content:
- URL → use WebFetch with prompt: "Return only the primary textual content, strip nav/footer/ads."
- Local file → use Read. For PDFs pass pages 1-20 by default; warn if >20 pages.
If schema hint is empty, propose a sensible default based on the content (e.g. news article → {title, date, author, entities, summary}).

Produce structured output in this format:

# Extracted from <source>

**Schema:** <inferred or user-provided>
**Extracted at:** <today's date>

```json
{
  ...structured data here...
}

Source grounding

: ""
...

Offer to save to ~/Desktop/ACTIVITIES/llm-wiki/extracts/<slug>-$(date +%Y%m%d).md if user says "save" / "yes".

Keep each quote ≤ 200 chars. Do not hallucinate fields not present in the source.

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.

4d ago First seen · 42 lines · 19 tokens per session scan A 886bf78efb09

Subscribe to this mod's changes

extract is a command published in the GitHub repository Achitokun14/claude-universal (2 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 356 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 2026-08-31.

Research ai-agents bash claude-code codex coding-agents gemini-cli

extract

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Source grounding

What this file has done since we first saw it

Other commands, from other repositories

dev-screenshot

publish

milestone-list

setup

fix

harness-adopt