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/AIgen-Solutions-s-r-l/agy-claude-pluginWrote 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/aigen-solutions-s-r-l/agy-claude-plugin/agy-panel)<a href="https://agentmods.dev/commands/aigen-solutions-s-r-l/agy-claude-plugin/agy-panel"><img src="https://agentmods.dev/badge/commands/aigen-solutions-s-r-l/agy-claude-plugin/agy-panel/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/aigen-solutions-s-r-l/agy-claude-plugin/agy-panel"><img src="https://agentmods.dev/badge/commands/aigen-solutions-s-r-l/agy-claude-plugin/agy-panel.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 | $0.00022 | $0.01165 |
| Opus 5 | $0.00011 | $0.00583 |
| Sonnet 5 | $0.00004 | $0.00233 |
| Haiku 4.5 | $0.00002 | $0.00117 |
Grade A, and why
agy-panel 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 10d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convene a panel: put the same question to several distinct models via
Antigravity (Google's agy CLI), then lay their answers side by side. The
user invoked: /agy-panel $ARGUMENTS
Everything in $ARGUMENTS is the PROMPT for every panellist. This command may
run only agy ... — nothing else (everything here is an agy call).
Before you run
Print a short progress line so the wait is expected, e.g.:
Convening an Antigravity panel (~30-90s; fanning out to N models)…
Pick the panel (validate every name — this is mandatory)
- List what's actually available:
agy models - Read that output. Choose N (default 3) verified-distinct models from different stables — e.g. a Gemini, a Claude, and GPT-OSS. Honour an explicit list if the user named models.
- Validate every chosen/requested name against the
agy modelsoutput.- If any name is not present in that list, ABORT the whole panel with a clear message naming the bad model and showing the available list.
- Landmine:
agy --model "<typo>"returns exit 0 and silently answers as the DEFAULT model. So a misspelt name does not error — it just gives you the default's answer wearing the wrong label. Never present such a fallback as a panel member. Only names that appear verbatim inagy modelsare eligible.
Run the panel (fan out in parallel, one-shot each)
Send the same prompt to each validated model in parallel (issue the calls together so they run concurrently):
agy --model "<name>" -p "<prompt>" --print-timeout 90s
- These are one-shot calls. NEVER use
-c/--continuehere. Landmine:agyconversation state is keyed by the current working directory and is last-writer-wins — fanning several models out with-cin the same cwd would clobber each other's history. So every panellist runs fresh. - Warn the user that, because a panel writes several conversations into the
same cwd-keyed slot, a plain
/agy -cafterwards is ambiguous (it continues whichever call wrote last, not "the panel"). If they want to follow up, they should re-ask with/agy --model <name>. - Per-model timeout / isolation: if one model errors or times out, do not block on it. Collect whatever finished and present partial results from the others, clearly noting which panellist failed and why.
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.
- 10d ago First seen · 95 lines · 22 tokens per session scan A 9923fef96fa0
agy-panel is a command published in the GitHub repository AIgen-Solutions-s-r-l/agy-claude-plugin (1 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 1,165 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
gemini-imagegen
Generate or edit an image via a Gemini (agy) session — Gemini's generateimage tool does what Claude cannot.
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.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
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/.
model
Show or set the agy (Antigravity / Gemini) model by writing /.gemini/antigravity-cli/settings.json — the reliable way to switch models (the unreliable --model flag silently falls back to the default). No agy call; takes effect immediately, no plugin reinstall.
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.