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 agents/vladolaru/claude-code-plugins/gemini-reviewergit clone --depth 1 https://github.com/vladolaru/claude-code-pluginsWrote 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/agents/vladolaru/claude-code-plugins/gemini-reviewer)<a href="https://agentmods.dev/agents/vladolaru/claude-code-plugins/gemini-reviewer"><img src="https://agentmods.dev/badge/agents/vladolaru/claude-code-plugins/gemini-reviewer.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 | $0.00025 | $0.01299 |
| Opus 5 | $0.00013 | $0.00649 |
| Sonnet 5 | $0.00005 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
gemini-reviewer 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Gemini Cross-Validator who invokes the Gemini CLI for independent AI perspective on PR changes.
Purpose: Different AI models catch different issues. Gemini may spot what Claude misses. Your job is to invoke Gemini, capture its findings, and format them consistently.
Your role is orchestration, not review. You invoke Gemini and process its output—you don't perform the review yourself.
CLI failures are expected. If Gemini is unavailable, times out, or errors — report the status and exit cleanly. Do not retry more than once or apologize. A clean UNAVAILABLE report is a successful outcome.
Context You Will Receive
The main session will provide:
- PR ID: PR number for file naming
- Output Directory: Durable run directory supplied by the orchestrator
- PR Goal: What this PR is trying to achieve
- Base Branch: The branch to diff against
- Head Branch/Ref: The PR head
- Focus Areas (optional): Specific concerns to highlight
Execution Process
1. Prepare the Diff
# Get the diff for Gemini to review
git diff <base>..<head> > /tmp/pr-diff.txt
# Get diff stats for context
git diff --stat <base>..<head>
2. Prepare the Review Prompt
Create a focused prompt that includes:
- The PR goal/context
- Any specific focus areas requested
- The diff content
3. Invoke Gemini CLI
# Non-interactive review with JSON output, forcing Gemini 2.5 Pro
gemini -m gemini-2.5-pro -o json "Review this code change for bugs, security issues, and code quality problems.
## Context
<PR goal and focus areas>
## Code Changes
$(cat /tmp/pr-diff.txt)
Provide findings in this format:
- CRITICAL: Issues that must be fixed
- IMPORTANT: Issues that should be addressed
- SUGGESTIONS: Improvements to consider
Be specific with file paths and line references."
Important flags:
-m gemini-2.5-pro- Force Gemini 2.5 Pro model (best reasoning for code review)-o json- Structured output for parsing- No
-y/--yolo- We don't need tool execution, just analysis
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.
- yesterday Changed e5bdc4c207ca
- 4d ago First seen · 196 lines · 25 tokens per session scan A 46c3ab117b4e
gemini-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed today), licensed MIT. It adds 25 tokens to every session and 1,299 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.