Agent Review

Get external AI agent feedback on code, architecture, and decisions

✨ The solution you've been looking for

Verified

Tested and verified by our team

6981 Stars

Get external agent review and feedback. Routes Anthropic models through Claude Agent SDK (uses local subscription) and other models through OpenRouter API. Use for code review, architecture feedback, or any external consultation.

code-review architecture debugging consultation multi-model openrouter agent-sdk feedback

Repository

See It In Action

Interactive preview & real-world examples

Live Demo

AI Conversation Simulator

See how users interact with this skill

User Prompt

Review this authentication code for security vulnerabilities

Skill Processing

Analyzing request...

Agent Response

Detailed security analysis highlighting potential vulnerabilities, OWASP compliance issues, and recommended fixes

Quick Start (3 Steps)

Get up and running in minutes

Install

claude-code skill install agent-review

claude-code skill install agent-review

Config

First Trigger

@agent-review help

Commands

Command	Description	Required Args
@agent-review security-code-review	Get an external security audit of authentication code	None
@agent-review architecture-validation	Validate design decisions with another AI perspective	None
@agent-review performance-analysis	Get algorithmic complexity and performance feedback	None

Typical Use Cases

Security Code Review

Get an external security audit of authentication code

Architecture Validation

Validate design decisions with another AI perspective

Performance Analysis

Get algorithmic complexity and performance feedback

Overview

Agent Review

Get feedback from an external AI agent. Useful for code review, architecture decisions, or getting a second opinion.

Running Commands

1echo "code or prompt" | node .claude/skills/agent-review/query.mjs [options] "Your question"
2# or
3node .claude/skills/agent-review/query.mjs --file <path> [options] "Your question"

Options

Flag	Short	Description
`--model <model>`	`-m`	Model or alias (default: gemini)
`--file <path>`	`-f`	Read input from file instead of stdin
`--lines <start-end>`	`-l`	Extract specific lines from file (e.g., 50-100)
`--context <path>`	`-c`	Additional context file (can repeat)
`--system <prompt>`	`-s`	Custom system prompt
`--temperature <n>`	`-t`	Temperature 0-1 (default: 0.7)
`--quiet`	`-q`	Suppress status messages and usage stats
`--list`		List available models
`--json`		Output raw JSON response

Available Models

Model ID	Aliases	Provider	Notes
`google/gemini-3-pro-preview`	`gemini`, `g3`	OpenRouter	Default - good for external perspective
`openai/gpt-5.1-codex`	`gpt`, `codex`, `gpt5`	OpenRouter	Strong at code analysis
`anthropic/claude-opus-4.5`	`opus`, `claude-opus`	Agent SDK	Uses local subscription
`anthropic/claude-sonnet-4.5`	`sonnet`, `claude`	Agent SDK	Uses local subscription

Anthropic models route through Claude Agent SDK (uses your Claude subscription). Other models route through OpenRouter API (requires OPENROUTER_API_KEY).

Environment Variables

Variable	Required	Description
`OPENROUTER_API_KEY`	For non-Anthropic models	OpenRouter API key
`AGENT_REVIEW_DEFAULT_MODEL`	No	Override default model

Examples

Code Review

1# Review a file for security issues
2cat src/server/auth.ts | node .claude/skills/agent-review/query.mjs \
3  "Review this authentication code for security vulnerabilities"
4
5# Review with a specific model (using alias)
6node .claude/skills/agent-review/query.mjs -m gpt -f src/utils/parser.ts \
7  "Review this parser for edge cases and error handling"

Reviewing Specific Lines

1# Review a specific function (lines 50-100)
2node .claude/skills/agent-review/query.mjs \
3  -f src/server/auth.ts -l 50-100 \
4  "Review this authentication function for security issues"
5
6# Review a single line
7node .claude/skills/agent-review/query.mjs \
8  -f src/utils/parser.ts -l 42 \
9  "Is this regex safe from ReDoS attacks?"

With Context Files

 1# Review code with type definitions as context
 2node .claude/skills/agent-review/query.mjs \
 3  -f src/api/routes.ts \
 4  -c src/types/api.ts \
 5  -c src/types/models.ts \
 6  "Review this API implementation"
 7
 8# Review component with its hooks as context
 9node .claude/skills/agent-review/query.mjs \
10  -f src/components/UserProfile.tsx \
11  -c src/hooks/useUser.ts \
12  "Review this React component for performance issues"

Architecture Feedback

1# Get feedback on a proposed design
2cat docs/design-proposal.md | node .claude/skills/agent-review/query.mjs \
3  "What are the potential issues with this architecture?"

Custom System Prompt

1node .claude/skills/agent-review/query.mjs \
2  -f src/api/routes.ts \
3  -s "You are a security expert specializing in API design" \
4  "Audit this API for OWASP top 10 vulnerabilities"

Temperature Control

1# Lower temperature for more deterministic analysis
2node .claude/skills/agent-review/query.mjs -t 0.2 -f src/algo.ts \
3  "Analyze the time complexity"
4
5# Higher temperature for creative suggestions
6node .claude/skills/agent-review/query.mjs -t 0.9 -f src/ui.tsx \
7  "Suggest ways to improve the user experience"

Using Anthropic Models (Local Subscription)

1# Uses Claude Agent SDK - no API credits consumed
2node .claude/skills/agent-review/query.mjs -m opus -f complex-algorithm.ts \
3  "Analyze the time complexity and suggest optimizations"

Quiet Mode (for scripting)

1# Suppress all status messages, only output the response
2REVIEW=$(node .claude/skills/agent-review/query.mjs -q -f src/auth.ts \
3  "List security issues as JSON array")
4echo "$REVIEW" | jq .

Output

The response text is written to stdout. After the response, usage stats are shown on stderr:

Tokens: 189 in / 871 out (1060 total)
Cost: $0.0108

This helps track token consumption and costs for OpenRouter requests. Use --quiet to suppress.

When to Use

Code Review: Get a second opinion on code quality, security, or performance
Architecture Decisions: Validate design choices with another perspective
Bug Analysis: Share error context and get debugging suggestions
Documentation Review: Check if docs are clear and complete
Test Coverage: Identify missing test cases

Tips

Default model (Gemini 3 Pro) is recommended for most external reviews
Use Anthropic models when you want consistency with Claude’s style
Use -l to review specific functions without sending the entire file (saves tokens)
Use -c to include type definitions or related files for better context
Use -t 0.2 for more focused/deterministic responses, -t 0.8 for creative suggestions
Pipe code directly for quick reviews: cat file.ts | node ... "review this"

What Users Are Saying

Real feedback from the community

Environment Matrix

Dependencies

Node.js (for executing query.mjs)

OPENROUTER_API_KEY for non-Anthropic models

Framework Support

Claude Agent SDK ✓ (for Anthropic models) OpenRouter API ✓ (for other models)

Model Compatibility

Google Gemini 3 Pro ✓ (recommended default)

OpenAI GPT-5.1 Codex ✓

Anthropic Claude Opus 4.5 ✓

Anthropic Claude Sonnet 4.5 ✓

Context Window

Token Usage Varies by model, supports file input with line ranges to optimize token usage

Security & Privacy

Information

Author: civitai
Updated: 2026-01-30
Category: productivity-tools

Agent Review

See It In Action

AI Conversation Simulator

Quick Start (3 Steps)

Install

Config

First Trigger

Commands

Typical Use Cases

Security Code Review

Architecture Validation

Performance Analysis

Overview

Agent Review

Running Commands

Options

Available Models

Environment Variables

Examples

Code Review

Reviewing Specific Lines

With Context Files

Architecture Feedback

Custom System Prompt

Temperature Control

Using Anthropic Models (Local Subscription)

Quiet Mode (for scripting)

Output

When to Use

Tips

What Users Are Saying

Environment Matrix

Dependencies

Framework Support

Model Compatibility

Context Window

Security & Privacy

Information

Related Skills

Agent Review

Pair Programming

Pair Programming