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.
git 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/delegate)<a href="https://agentmods.dev/commands/yuting0624/antigravity-for-claude-code/delegate"><img src="https://agentmods.dev/badge/commands/yuting0624/antigravity-for-claude-code/delegate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/yuting0624/antigravity-for-claude-code/delegate"><img src="https://agentmods.dev/badge/commands/yuting0624/antigravity-for-claude-code/delegate.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00024 | $0.00977 |
| Opus 5.5 | $0.00010 | $0.00391 |
| Sonnet 5.5 | $0.00005 | $0.00195 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
delegate 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 1mo 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
Delegate the following task to Antigravity (agy / Gemini) via the plugin wrapper,
following the antigravity skill's Cost discipline and Verification gates.
Task: $ARGUMENTS
Do this:
- Pick a tier (
flashdefault;profor hard reasoning). If the task needs the repo, add--dir <repo-root>so agy reads the real files (don't paste them into context). If the task WRITES files or uses tools (web search / URL reads / Vertex AI Search / terminal), it needs a grant. For a plain file write the narrower one is awrite_file(<dir>)entry underpermissions.allowin~/.gemini/antigravity-cli/settings.json(recursive beneath<dir>, no flag needed — substitute a real path for<dir>; if a rule is already there and the write is still denied,agy-doctorchecks whether agy can parse it). Otherwise pass--yolo, which auto-approves all tools and is what web search / URL reads (agy 1.1.28+) / Vertex AI Search / terminal need. Without a grant, headless agy leaves your workspace untouched, and since 1.1.3 the run says so on stderr (it describes / scratch-diverts / soft-denies / fails outright depending on version; issue #10).--mode accept-editsis not a grant either: measured on agy 1.1.13, where the flag is applied at all, the write is denied exactly like one without it. Run write tasks on a dedicated branch —--sandboxis not containment, it was measured doing nothing under--yolo— and verify files actually changed withgit status. Claude Code may prompt for or block--dangerously-skip-permissions— approve it or pre-allow it; non-interactive (claude -p) without that permission can't write/use-tools via agy. (If the wrapper returns exit15, that's exactly this: agy denied the write. Both shapes land here — the soft deny on agy 1.1.3+ (back again from 1.1.20, measured on 1.1.25) and the hard error on 1.1.13–1.1.19 — and both take the same fix: apermissions.allowrule covering the target, or--yolo. Since agy 1.1.27 the wrapper names the refused tool from the envelope'sdenied_actions.) - Run synchronously (you may be headless — do not background-and-wait):
agy-delegate --tier <tier> [--dir .] [--yolo] [--digest] "<task>"For read/analysis tasks, add--digest— it appends a digest-only output contract so agy returns compact bullets instead of raw content. - Ingest only the result/digest — do NOT re-read the files agy already handled
(keeps your context lean; that's where the cost savings come from). If the wrapper
prints a "looks like a raw dump" note on stderr, do NOT ingest the raw output —
re-run with
--digestor ask agy to summarize it first. - Verify: actually run/check the output; never trust a self-reported "done". Report what you delegated and how you verified it.
Remember the break-even: only delegate if the offloaded volume clearly exceeds the spec + round-trip + verification overhead. Tiny tasks are cheaper to just do yourself.
Long task, interactive session? A sync delegation can also hit Claude Code's ~2-min
Bash-tool limit — start it in the background and keep working (this also keeps the prompt
cache warm and frees you to do other turns):
ID=$(agy-job start --tier pro --dir . "<task>")
then check /antigravity:status and collect with /antigravity:result <id>.
(Don't do this when YOU are headless claude -p — one-shot, no later turn to collect;
delegate synchronously there.)
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.
- 1mo ago Changed · +1 lines b75f3640933f
- 1mo ago Changed · +1 lines dd49235009e3
- 1mo ago First seen · 53 lines · 24 tokens per session scan A 103bf629c50c
delegate is a command published in the GitHub repository yuting0624/antigravity-for-claude-code (412 stars, last pushed 6d ago), licensed MIT. It adds 24 tokens to every session and 977 once invoked, about $0.0001 per session on Opus 5.5. 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.
setup-video-vision
Interactive setup wizard for claude-video-vision — configure backend, whisper, frames, and verify dependencies.
report
Generate a publication-grade HTML report from a markdown source using the TRAID Design System catalog (5 templates). Agy matches content to template, you confirm, agy produces final branded HTML.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
design-review
Run a UX/visual design audit of a URL using Antigravity (agy). Captures desktop + mobile screenshots, scores 10 dimensions (hierarchy, typography, color, spacing, a11y, etc.), benchmarks against industry. Saves to docs/agy/design-reviews/.
media
Ask a question about an AUDIO, VIDEO or IMAGE file (or a YouTube/remote URL) with Antigravity (agy / Gemini 3.x multimodal). Beyond transcription — "what decisions were made in this meeting?", "what happens at 2:30 in the video?", "what's the tone of this voice note?". Claude Code can't see/hear media; agy can.