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/modelgit 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/model)<a href="https://agentmods.dev/commands/marcosnahuel/antigravity-plugin-cc/model"><img src="https://agentmods.dev/badge/commands/marcosnahuel/antigravity-plugin-cc/model.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 | $0.00059 | $0.01073 |
| Opus 5 | $0.00030 | $0.00536 |
| Sonnet 5 | $0.00012 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00107 |
Grade A, and why
model 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Show or change which model agy --print uses. agy reads the active model from
~/.gemini/antigravity-cli/settings.json ("model": "<label>"); the TUI's "Switch Model"
just writes that key. The --model CLI flag is unreliable (an unknown id silently falls
back to the default), so this command edits settings.json directly. The change is immediate —
no plugin reinstall.
Raw user request: $ARGUMENTS
Alias table (canonical copy: config/model-map.json — keep in sync)
| Alias | Label written to settings.json |
|---|---|
flash-low |
Gemini 3.5 Flash (Low) |
flash / flash-medium |
Gemini 3.5 Flash (Medium) |
flash-high |
Gemini 3.5 Flash (High) |
pro / pro-low |
Gemini 3.1 Pro (Low) |
pro-high |
Gemini 3.1 Pro (High) |
sonnet |
Claude Sonnet 4.6 (Thinking) |
opus |
Claude Opus 4.6 (Thinking) |
gpt-oss |
GPT-OSS 120B |
(Low/Medium/High) is the thinking-effort level. Model availability depends on the account
tier (free = Flash / Flash-Lite only). For /agy:notebook sweeps, flash-low is fastest/cheapest;
use pro for higher-quality synthesis.
What to do (ONE Bash call)
Run this, substituting the requested alias/label (trim $ARGUMENTS; empty = show only). It accepts
an alias OR a full quoted label verbatim (so you can paste an exact string from the TUI when an
alias is stale):
ARG="$ARGUMENTS" # the alias or exact label, or empty
python - "$ARG" <<'PY'
import json, os, sys, shutil
arg = (sys.argv[1] if len(sys.argv) > 1 else "").strip().strip('"').strip("'")
sp = os.path.expanduser("~/.gemini/antigravity-cli/settings.json")
ALIASES = {
"flash-low":"Gemini 3.5 Flash (Low)", "flash":"Gemini 3.5 Flash (Medium)",
"flash-medium":"Gemini 3.5 Flash (Medium)", "flash-high":"Gemini 3.5 Flash (High)",
"pro":"Gemini 3.1 Pro (Low)", "pro-low":"Gemini 3.1 Pro (Low)",
"pro-high":"Gemini 3.1 Pro (High)", "sonnet":"Claude Sonnet 4.6 (Thinking)",
"opus":"Claude Opus 4.6 (Thinking)", "gpt-oss":"GPT-OSS 120B",
}
try:
cfg = json.load(open(sp, encoding="utf-8"))
except FileNotFoundError:
cfg = {}
cur = cfg.get("model", "(unset — agy uses its default)")
if not arg:
print("Modelo actual:", cur)
print("\nAlias disponibles:")
for a, lbl in ALIASES.items(): print(f" {a:13} → {lbl}")
print("\nUso: /agy:model <alias> o /agy:model \"Gemini 3.1 Pro (High)\"")
sys.exit(0)
label = ALIASES.get(arg.lower(), arg) # alias → label, else use verbatim
shutil.copyfile(sp, sp + ".bak") if os.path.exists(sp) else None
cfg["model"] = label
json.dump(cfg, open(sp, "w", encoding="utf-8"), ensure_ascii=False, indent=2)
print(f"Modelo: {cur} → {label}")
if arg.lower() not in ALIASES and arg != label:
print("(usaste un label literal; verificá que coincida exacto con la lista del TUI)")
print("⚠️ Si agy sigue en el modelo anterior, el label no coincide con tu cuenta: abrí el TUI"
" `agy` → Switch Model, copiá el string exacto y reintentá con /agy:model \"<label>\".")
PY
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 · 77 lines · 59 tokens per session scan A d7c7dd27f99b
model is a command published in the GitHub repository MarcosNahuel/antigravity-plugin-cc (26 stars, last pushed 19d ago), licensed MIT. It adds 59 tokens to every session and 1,073 once invoked, about $0.0003 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-panel
Ask Antigravity (agy) the same question across several distinct models and compare their answers side by side.
agy
Consult Google's Antigravity CLI (agy) and relay its answer.