scrape

scrape is a command for coding agents from MarcosNahuel/antigravity-plugin-cc. It costs 30 tokens per session (705 once invoked), scanned A, original, MIT.

A command that extracts structured information from one web page and returns it as a Markdown table or JSON. It saves the result in a local documentation folder.

In plain words
What is it for?
Use it to collect specified fields from a URL for documentation or later processing.
Why use it?
It avoids copying page details by hand and gives the extracted information a consistent format.

Command

Part of the antigravity plugin — 2 skills, 22 commands, 1 agent 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 commands/marcosnahuel/antigravity-plugin-cc/scrape
Clone the repo
git clone --depth 1 https://github.com/MarcosNahuel/antigravity-plugin-cc

Or install antigravity, the plugin that ships this one along with the rest of its 2 skills, 22 commands, 1 agent.

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 scrape

README.md
[![agentmods](https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/scrape.svg)](https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/scrape)
Your own site
<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/scrape"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/scrape.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 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 $0.00030 $0.00705
Opus 5 $0.00015 $0.00352
Sonnet 5 $0.00006 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 5d ago against content hash f13d4eed7205, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scrape 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 5d 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.

plugins/antigravity/commands/scrape.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Route this to the antigravity:agy-rescue subagent in MODE: scrape.

Raw user request: $ARGUMENTS

Routing rules

  1. Parse the URL: the first whitespace-separated token of $ARGUMENTS that starts with http:// or https:// IS the URL. If the user wrote it without a scheme, prepend https://. If no URL is found, ask once: "What URL should I scrape?".

  2. Parse --json: if present, set FORMAT=json and strip the flag from the remaining text. Default is FORMAT=md.

  3. Schema/description: everything else in $ARGUMENTS (whatever is not the URL and not --json) is the schema or natural-language extraction description. If empty, agy will infer reasonable fields from the page.

  4. Slug: build from the URL's host + first path segment (lowercase, non-alphanumeric → -, collapse repeats, trim to 60 chars).

  5. Date: today in YYYY-MM-DD (local time).

  6. Paths (relative to current working directory):

    • OUTPUT_DIR = docs/agy/scrapes/
    • WRITE_FILE = docs/agy/scrapes/<date>-<slug>.md (or .json if --json)
  7. Pre-flight (ONE Bash call):

    mkdir -p docs/agy/scrapes
    
  8. Hand off: pass this header to the subagent:

    MODE: scrape
    URL: <url>
    SCHEMA: <schema or natural-language description, or empty>
    FORMAT: md|json
    CWD: <absolute path to current working directory>
    WRITE_FILE: docs/agy/scrapes/<date>-<slug>.md
    

Operating rules

  • The subagent invokes agy with --add-dir <CWD> so it can write the scrape report into the project.
  • The subagent reports:
    1. Saved scrape path.
    2. First ~30 lines of the scrape result (preview).
    3. Number of records/fields extracted.
  • Present that to the user as-is.
  • If the URL returns non-200, the page is blocked by anti-bot, or the structure cannot be parsed, surface the error verbatim.

Notes

  • For JSON-API endpoints, --json is preferred. For HTML landing pages or content sites, default md table is usually more readable.
  • agy uses its browser/read_url tool to fetch — JS-heavy SPAs require the browser subagent (slower but works). Static HTML works via read_url (faster).
  • agy uses an isolated Chrome profile if it needs to render JS — no cookies, no logged-in state.
  • For aggressive scraping (anti-bot bypass), this is the wrong tool. Use BrightData / ScrapingBee.

Read the full file on GitHub · 61 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. 5d ago First seen · 61 lines · 30 tokens per session scan A f13d4eed7205

Subscribe to this mod's changes

scrape is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (26 stars, last pushed 19d ago), licensed MIT. It adds 30 tokens to every session and 705 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.