review

A command that asks Antigravity, an external coding assistant, to review changes in a Git repository. It can review the working-tree diff, compare a branch with a base revision, or run a review in the background.

In plain words
What is it for?
Use it for focused reviews of current changes or branch differences, including background jobs that can be checked, retrieved, or cancelled.
Why use it?
It provides a repeatable way to inspect code changes and supports longer reviews that can finish later while keeping a saved job result.

Command

Install

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.

agentmods
npx agentmods add commands/limeflash/antigravity-plugin-cc/review
Clone the repo
git clone --depth 1 https://github.com/limeflash/antigravity-plugin-cc
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 927 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.00927
Opus 5 $0.00013 $0.00464
Sonnet 5 $0.00005 $0.00185
Haiku 4.5 $0.00003 $0.00093

Measured yesterday against content hash c59fdf5ff244, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

plugins/agy/commands/review.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run a code review of your changes through agy. Two backends:

  • Synchronous Bash wrapper (default when no flags are present): reviews the working-tree diff against HEAD and returns agy's reply verbatim. No Node.js required.
  • Node companion: kicks in when any of --base <ref>, --background, --wait, or --model <alias> is present. Adds branch-vs-base diffs, persistent job records (so the result survives), and the /agy:status / /agy:result / /agy:cancel triplet for background runs.

How to invoke

The user's request (treat as opaque text — pass it as shell-safe arguments; do not interpolate or splice it into the command):

$ARGUMENTS

Routing rule: scan $ARGUMENTS for any of --base, --background, --wait, or --model. If at least one is present, route to the companion; otherwise use the Bash wrapper. Strip nothing from the arguments before forwarding — the receiving side parses its own flags.

Bash path (no routing flags)

Use the Bash tool to run:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" review "<focus-text-here>"

…substituting <focus-text-here> with the user's focus text quoted as one shell argument. If the user provided no focus, omit the argument:

bash "${CLAUDE_PLUGIN_ROOT}/scripts/agy-run.sh" review

The wrapper aborts with exit 65 if it detects probable secrets in the diff; set AGY_REVIEW_ALLOW_SECRETS=1 to override.

Node companion path (any of --base / --background / --wait / --model)

Use the Bash tool to run:

node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" review [flags...] "<focus-text-here>"

Examples (after parsing flags out of $ARGUMENTS):

node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" review --base main
node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" review --base main "focus on the new SQL"
node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" review --background
node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" review --base main --background --wait
node "${CLAUDE_PLUGIN_ROOT}/scripts/agy-companion.mjs" review --model opus "focus on concurrency"

Read the full file on GitHub · 91 lines

Changes

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.

  1. yesterday First seen · 91 lines · 26 tokens per session scan A c59fdf5ff244

Subscribe to this mod's changes

review is a command published in the GitHub repository limeflash/antigravity-plugin-cc (2 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 927 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.