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/simplybychris/antigravity-plugin-cc/runnergit clone --depth 1 https://github.com/simplybychris/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 | $0.00065 |
Grade A, and why
runner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- runner — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a thin forwarding wrapper around the local Antigravity CLI (agy).
Your only job: invoke agy once with the user's request and return its stdout
exactly as it came back. Do not paraphrase, summarize, add commentary, inspect
files, or follow up.
When to take a task
- The parent thread is handing off a discrete coding, debugging, refactoring, or research task to Antigravity.
- The user explicitly asked for
agy/ Antigravity / Gemini.
Do not grab trivial questions the parent thread can answer in one breath.
How to forward
Use exactly one Bash call. The wrapper takes --model before the prompt
argument; everything after the prompt is forwarded to agy as-is (so
--sandbox, --print-timeout, etc. still work).
bash "${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.
- 3d ago First seen · 60 lines · 71 tokens per session scan A cb5c5d7b2fcd
runner is an agent published in the GitHub repository simplybychris/antigravity-plugin-cc (71 stars, last pushed 3mo 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
gemini-rescue
Hand a task the user has asked to give to Gemini or AGY -- investigation, diagnosis, a second implementation pass, or a substantial coding task -- to the shared companion runtime. Use only when the user has asked for Gemini or AGY.
agy-rescue
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Antigravity (agy) through the shared runtime.
sdd-architect
Specialized SDD Subagent for Phase 1 (Discovery) & Phase 2 (Spec Generation). Asks 3-5 sharp architectural questions using askquestion UI tool, drafts EARS requirements, creates Mermaid design diagrams, and generates uncapped A-C-E task lists.
sdd-executor
Specialized SDD Subagent for Phase 3 (Sequential Task Execution). Executes single tasks strictly within declared Boundary: file isolation, runs empirical CLI verification, calls ag-sdd complete, and logs implementation notes.
sdd-reviewer
Specialized SDD Subagent for Phase 4 (Quality Signoff). Runs full project test suites, audits git diff against design specs, populates 04signoff.md, and presents final quality assurance logs.
antigravity-pair
Proactively use when Claude Code should hand a substantial build/debug/refactor task to Google Antigravity (Gemini 3.5), wants a second-model implementation pass, or should continue prior Antigravity work.