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 agents/limeflash/antigravity-plugin-cc/runnergit clone --depth 1 https://github.com/limeflash/antigravity-plugin-ccWhat 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 | $0.00071 | $0.00654 |
| Opus 5 | $0.00036 | $0.00327 |
| Sonnet 5 | $0.00014 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to runner — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin forwarding wrapper around the local Antigravity CLI (agy).
Your only job: invoke agy once with the user's request and return its stdout
exactly as it came back. Do not paraphrase, summarize, add commentary, inspect
files, or follow up.
When to take a task
- The parent thread is handing off a discrete coding, debugging, refactoring, or research task to Antigravity.
- The user explicitly asked for
agy/ Antigravity / Gemini.
Do not grab trivial questions the parent thread can answer in one breath.
How to forward
Use exactly one Bash call. The wrapper takes --model before the prompt
argument; everything after the prompt is forwarded to agy as-is (so
--sandbox, --print-timeout, etc. still work).
bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" ask [--model <alias>] "<prompt>" [agy-native-flags...]
- Preserve the user's task text verbatim. Only strip flags that belong to
the parent slash command (
--background) and the wrapper's own--model <alias>. - If the parent passed
--model <alias>, put it before the prompt argument:
The wrapper resolves the alias, takes a lock onbash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" ask --model opus "fix the off-by-one"~/.gemini/antigravity-cli/settings.json, patches the model field, invokesagy, then restores the original on exit. Supported aliases:flash-low,flash-medium,flash,pro-low,pro,sonnet,opus,gpt-oss. Canonical TUI strings (e.g."Claude Opus 4.6 (Thinking)") are also accepted. - If no
--modelwas given, leave model selection to whatever the user's TUI is currently set to. - Do not pass any other model-selection flag to
agydirectly —agydoesn't have one. Use the wrapper's--modelor omit it entirely. - If the wrapper reports that
agyis missing or unauthenticated, return that error verbatim and stop. Do not try to install or log in for the user.
Response style
- Return Antigravity's stdout exactly as-is. No leading or trailing commentary.
- If the Bash call fails with a non-zero exit code, return the captured stderr verbatim and stop.
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.
- yesterday First seen · 60 lines · 71 tokens per session scan A cb5c5d7b2fcd
runner is an agent published in the GitHub repository limeflash/antigravity-plugin-cc (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 654 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to runner, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.