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/yuting0624/antigravity-for-claude-code/researchgit clone --depth 1 https://github.com/yuting0624/antigravity-for-claude-codeWrote 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/yuting0624/antigravity-for-claude-code/research)<a href="https://agentmods.dev/commands/yuting0624/antigravity-for-claude-code/research"><img src="https://agentmods.dev/badge/commands/yuting0624/antigravity-for-claude-code/research.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 | $0.00034 | $0.00562 |
| Opus 5 | $0.00017 | $0.00281 |
| Sonnet 5 | $0.00007 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
research 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.
What it actually says
Run a multi-source research pass on the topic below, following the antigravity
skill's Deep-research recipe and Verification gates. Antigravity (agy / Gemini)
is the cheap, grounded search worker; you (Claude) own the plan, the verification, and
the synthesis. agy's print-mode citations are coarse (often domain-level) and it can
present parametric "knowledge" as a sourced fact — so never ship its citations unchecked.
Topic: $ARGUMENTS
If the topic is empty, ask the user what to research (AskUserQuestion) before starting.
Do this:
- Plan (you). Break the topic into 3–6 sub-questions and list the load-bearing claims that must be verified. You own scope and final synthesis.
- Fan-out fetch (agy, cheap, one call per sub-question). Web search needs
--yoloin headless mode; force compact output so bulky pages stay on Gemini's side, not yours:agy-delegate --tier flash --yolo "Web-search <sub-question>. Return 5–8 bullet findings, each with the exact source URL and publication date. Output ONLY findings + URLs + dates." - Deepen on each load-bearing claim (agy). Name the URL and have agy quote the supporting sentence(s), turning domain-level citations into verifiable quotes:
agy-delegate --tier pro --yolo "Open <URL> and quote the exact sentence(s) supporting: '<claim>'. If the page does not support it, reply NOT SUPPORTED." - Adversarially verify (you). Corroborate each key claim across ≥2 independent domains; treat any single / vague / domain-only citation as unverified; sanity-check dates; watch for Gemini parametric knowledge posing as a sourced fact.
- Synthesize (you). Write a cited report from verified findings only; explicitly mark anything uncorroborated as "unverified".
Keep your own context lean — ingest agy's bullet digests, not the raw pages (that's where the cost savings come from). --print does one agentic pass per call, so re-dispatch follow-up agy calls to close gaps rather than expecting it to auto-iterate. In an interactive session a long fetch can be backgrounded with agy-job; when you are headless (claude -p), delegate synchronously.
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 · 26 lines · 34 tokens per session scan A 6810e828f42c
research is a command published in the GitHub repository yuting0624/antigravity-for-claude-code (305 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 562 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
agy
Delegate any task to agy (Google Antigravity CLI) — auto-selects model by task type.
ask
Query multiple AI agents (Gemini, OpenAI, Grok, Perplexity, Kimi, and a local ollama model) for diverse perspectives on architecture decisions, technology choices, debugging dead-ends, and security tradeoffs. Use this whenever the user names the council directly, whatever the topic — ask the council, council review…
result
Fetch, list, or cancel background council jobs started with --async.
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
notebook
Local NotebookLM over a FOLDER of documents using Antigravity (agy). Sweeps each document (PDF with text, scanned PDF, image, docx) into an objective-driven Markdown summary, then builds a relevance INDEX and a cited master summary. Incremental cache (re-runs only re-summarize changed docs / changed objective) and…
deep-research
Deep, multi-source, fact-checked web research with agy — reach for it when a decision or design depends on getting it right and a single-shot answer is not enough (architecture / tool / vendor choices, thorough landscape scans, anything you will act on). Builds an evidence matrix + a plan you approve, then agy browses…