gemini-review

gemini-review is a skill for Claude Code from freestyler-arb/imagine-gemini-for-claude-codex. It costs 102 tokens per session (1,046 once invoked), scanned A, original, MIT.

A skill that sends code, changes, pull requests, architecture decisions, or plans to Google Gemini for an independent, adversarial review. Adversarial review means actively looking for real defects and edge cases.

In plain words
What is it for?
Use it to review a file, diff, pull request, architecture choice, or plan and receive severity-labelled findings with concrete fixes.
Why use it?
A second AI model can spot correctness, security, or design problems that the first review missed.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the imagine plugin — 4 skills shipped together

Good fit Use it to review a file, diff, pull request, architecture choice, or plan and receive severity-labelled findings with concrete fixes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-review
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.

Any agent
npx skills add freestyler-arb/imagine-gemini-for-claude-codex --skill gemini-review
Clone the repo
git clone --depth 1 https://github.com/freestyler-arb/imagine-gemini-for-claude-codex

Made for: Claude Code.

Or install imagine, the plugin that ships this one along with the rest of its 4 skills.

Wrote 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.

agentmods badge for gemini-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-review/github.svg)](https://agentmods.dev/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-review)
Your own site
<a href="https://agentmods.dev/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-review"><img src="https://agentmods.dev/badge/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-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.

agentmods 80×15 button for gemini-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-review"><img src="https://agentmods.dev/badge/skills/freestyler-arb/imagine-gemini-for-claude-codex/gemini-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 102 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00102 $0.01046
Opus 5 $0.00051 $0.00523
Sonnet 5 $0.00020 $0.00209
Haiku 4.5 $0.00010 $0.00105

Measured 12d ago against content hash 8c4e2f92301f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

gemini-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 12d 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.

skills/gemini-review/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gemini-review

Overview

Get a structured, adversarial review from Google Gemini as a second pair of eyes. Different model families fail differently, so Gemini frequently flags correctness bugs, edge cases, and security issues that the main agent's own review misses. The review runs on the user's AI Pro subscription (agy) and does not spend the main agent's tokens.

This is a specialised wrapper around gemini-pro: same delegation mechanics, but with a fixed review prompt and a severity-tagged output format. For freeform delegation use gemini-pro; for research/digestion use gemini-research.

How to invoke

Pipe the artifact under review via stdin and ask for a structured review. Use the default Pro/High model — review quality matters more than quota here.

# A single file
cat src/order_engine.py | gemini "$(cat <<'PROMPT'
You are a senior engineer doing an adversarial code review. Find real defects only.
For each finding give: [SEVERITY: critical|high|medium|low] — file/area — the bug —
why it is wrong — a concrete fix. End with a one-line overall verdict (ship / fix-first).
Do NOT invent issues; if the code is fine, say so. Focus on:
correctness bugs, race conditions, edge cases, error handling, security, and data loss.
PROMPT
)"

# A diff / PR
git diff main...HEAD | gemini "Adversarial review of this diff. Same format: [SEVERITY] — area — bug — why — fix. Only real defects."

If gemini is not on PATH use ~/.local/bin/gemini or agy -p "<prompt>" --model "Gemini 3.1 Pro (High)".

Steps

  1. Collect the exact artifact — a file, a set of files, git diff, or a written plan. Smaller and focused beats dumping the whole repo.
  2. Strip secrets (API keys, tokens, private data) before piping. Never send credentials to an external model.
  3. Write the review prompt stating the role, what to look for, the severity format, and the "no invented issues" guardrail. Add domain constraints the reviewer must respect (invariants, perf budgets, API contracts) — Gemini has none of this session's context.
  4. Run it (Pro/High, ~20–90s; Bash timeout ~120000 ms).
  5. Triage the findings yourself. Confirm each against the actual code before acting — Gemini can produce confident false positives. Relay a synthesised, de-duplicated list, attributed to Gemini, with your own verdict on which findings are real.

Read the full file on GitHub · 63 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. 12d ago First seen · 63 lines · 102 tokens per session scan A 8c4e2f92301f

Subscribe to this mod's changes

gemini-review is a skill published in the GitHub repository freestyler-arb/imagine-gemini-for-claude-codex (4 stars, last pushed 2mo ago), licensed MIT. It adds 102 tokens to every session and 1,046 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

reviewer

Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /agy:reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent verifier…

keli-wen/agy-staff · 94 tokens

codex

Route a task to OpenAI's Codex CLI (codex exec) instead of doing it yourself. Use this skill ANY time the user names codex or types /codex — even for routine work Claude could handle, because the user is choosing to delegate. The intent: 'ask codex', 'have codex review/refactor this', 'check/validate with codex', 'see…

sparklingneuronics/sparkling-skills · 249 tokens

agy

Route a task to Google Antigravity's agy CLI — the multi-model successor to gemini-cli. Use this skill ANY time the user names agy, antigravity, OR gemini, or types /agy or /gemini — even for routine work. Runs multiple models (Gemini 3.x, Claude 4.6, GPT-OSS): 'gemini' picks a Gemini model, 'agy'/'antigravity' the…

sparklingneuronics/sparkling-skills · 263 tokens

vibe-code-auditor

Audit rapidly generated or AI-produced code for structural flaws, fragility, and production risks. Use when evaluating prototype or AI-generated code for production readiness.

bcastelino/agent-skills-kit · 37 tokens

agy-reviewer

Get a second-opinion review from Google's Antigravity CLI (agy staffer, fast Gemini) - of code (a diff, PR, working tree) or of a decision, plan, or design. Use when the user says /skill:agy-reviewer, "have agy review this", "second opinion on my diff/PR/plan", or after finishing work and wanting an independent…

keli-wen/agy-staff · 96 tokens

antigravity-result-handling

How to interpret Antigravity companion output — successful responses, quota/auth/backend errors, and applying file changes.

Idun-Group/antigravity-plugin-cc · 28 tokens