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-review)<a href="https://agentmods.dev/commands/aigen-solutions-s-r-l/agy-claude-plugin/agy-review"><img src="https://agentmods.dev/badge/commands/aigen-solutions-s-r-l/agy-claude-plugin/agy-review/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-review"><img src="https://agentmods.dev/badge/commands/aigen-solutions-s-r-l/agy-claude-plugin/agy-review.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 | $0.00020 | $0.01657 |
| Opus 5 | $0.00010 | $0.00829 |
| Sonnet 5 | $0.00004 | $0.00331 |
| Haiku 4.5 | $0.00002 | $0.00166 |
Grade A, and why
agy-review 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 11d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Have Antigravity (Google's agy CLI) review my current change set as a
senior reviewer, then relay its findings. The user invoked:
/agy-review $ARGUMENTS
Everything in $ARGUMENTS is optional extra focus for the reviewer — except
--deep, which is our flag (not agy's) and is stripped before building
the prompt.
Before you run
Print a short progress line so the wait is expected, e.g.:
Reviewing your changes with Antigravity (~30s-3m, agentic CLI)…
Gather the change context (git only)
Collect the diff with git, in this order — use the first that is non-empty:
- Staged changes (a deliberate commit boundary):
git diff --staged - Else working tree vs HEAD (uncommitted edits):
git diff HEAD - Else branch vs main (already-committed work on this branch). Resolve the
base first and only use it if it exists:
git rev-parse --verify main git diff main...HEAD
Also grab git status --short and git log --oneline -5 for orientation.
Bound it (hard cap — never blow past this)
The diff must be capped before it leaves the machine:
- Hard cap: ~600 lines and ~24 KB, whichever is hit first.
- If the diff is over the cap, do not send the whole thing. Instead send
git diff --statplus the diffs of only the changed files that fit, and add a line noting that the review was truncated to fit the cap (list which files were included vs omitted). - Never include secrets,
.envfiles, or any.gitignoredfiles. If the diff touches such a path, drop that hunk and note the omission.git diffalready excludes ignored files; do not override that.
Consent line (always visible)
Before sending, print exactly one line stating what leaves the machine, e.g.:
Attaching <N lines / M files> to Antigravity (Google) — code leaves the machine.
Fill in the real counts from the bounded diff.
Transport via a dedicated temp dir
Put only the bounded, consented context into a fresh temp directory and hand
that to agy with --add-dir (so nothing else in the repo is exposed):
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.
- 11d ago First seen · 151 lines · 20 tokens per session scan A 556092596b79
agy-review 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 20 tokens to every session and 1,657 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
review
Send the current git diff to Antigravity (agy) for code review. Optional focus text to steer the review.
done
Finish a task - document, create PR or merge, close.
worktree
Worktree lifecycle management - create, list, remove, info on interactive worktrees.
end
End a work session - a settlement pass that reconciles uncommitted / unpushed work + session context into git, the tracker, and a session snapshot file. --session (aliases --snapshot, --pre-compact, --compact) skips settlement and only writes the shared snapshot, keeping the session going.
release
A command that carries out a release workflow for the nanobanana-adc project, including version checks, changelog updates, tests, builds, and release preparation.
gemini-imagegen
Generate or edit an image via a Gemini (agy) session — Gemini's generateimage tool does what Claude cannot.