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 commands/marcosnahuel/antigravity-plugin-cc/scrapegit clone --depth 1 https://github.com/MarcosNahuel/antigravity-plugin-ccWrote 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.
[](https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/scrape)<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>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 | $0.00030 | $0.00705 |
| Opus 5 | $0.00015 | $0.00352 |
| Sonnet 5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
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.
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
-
Parse the URL: the first whitespace-separated token of
$ARGUMENTSthat starts withhttp://orhttps://IS the URL. If the user wrote it without a scheme, prependhttps://. If no URL is found, ask once: "What URL should I scrape?". -
Parse
--json: if present, setFORMAT=jsonand strip the flag from the remaining text. Default isFORMAT=md. -
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. -
Slug: build from the URL's host + first path segment (lowercase, non-alphanumeric →
-, collapse repeats, trim to 60 chars). -
Date: today in
YYYY-MM-DD(local time). -
Paths (relative to current working directory):
OUTPUT_DIR=docs/agy/scrapes/WRITE_FILE=docs/agy/scrapes/<date>-<slug>.md(or.jsonif--json)
-
Pre-flight (ONE
Bashcall):mkdir -p docs/agy/scrapes -
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:
- Saved scrape path.
- First ~30 lines of the scrape result (preview).
- 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,
--jsonis preferred. For HTML landing pages or content sites, defaultmdtable 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.
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.
- 5d ago First seen · 61 lines · 30 tokens per session scan A f13d4eed7205
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.
Other commands, from other repositories
gemini-swarm
Swarm a task across parallel Gemini (agy) sessions with automatic decomposition and model routing.
gemini-imagegen
Generate or edit an image via a Gemini (agy) session — Gemini's generateimage tool does what Claude cannot.
agy-debug
Send an error/stack trace plus the relevant file(s) to Antigravity (agy) for root-cause analysis.
agy-review
Send the current change set to Antigravity (agy) for a senior-reviewer code review.
agy
Consult Google's Antigravity CLI (agy) and relay its answer.
agy-panel
Ask Antigravity (agy) the same question across several distinct models and compare their answers side by side.