Code Review Agent
★TrustedMIT★Gold Verified100Agentby AgentNode · published 14 days ago · agent
Perform comprehensive code review: lint, security audit, refactoring suggestions, and best practices check.
Review code by running linting, checking for security vulnerabilities, suggesting refactorings, and verifying adherence to best practices, then produce a review report. This agent uses AgentNode's full skill registry to dynamically discover and install the capabilities it needs at runtime.
Quick Start
agentnode install code-review-agentRuns in a subprocess with filtered environment by default. Declared permissions are policy-checked, not sandboxed.
Usage
Generated templatefrom code_review_agent.agent import run
result = run()
print(result)Runs locally on your machine. No execution data is sent to AgentNode. Permissions are checked before execution. Learn how this works
AAgent Configuration
Tier
LLM + ToolsGoal
Review code by running linting, security checks, and suggesting refactorings.
Agent Behavior
description onlyYou are a senior code reviewer. Perform comprehensive code review: run linting, check for security vulnerabilities, suggest refactoring improvements, and assess code quality. Produce an actionable review report.
Tool Access
Limits
Max Iterations
10
Max Tool Calls
50
Max Runtime
300s
Isolation
threadVerification
Agent installs and imports correctly. runtime checks passed. 2/2 verification cases passed. manifest completeness 10/10.
This package was executed and validated by AgentNode before listing. Install, import, and runtime checks passed.
Last verified 14d ago· Runner v2.0.0
Version History
Capabilities
Perform comprehensive code review: lint, security audit, and refactoring suggestions.
Input Schema
{
"type": "object",
"required": [
"goal"
],
"properties": {
"goal": {
"type": "string",
"description": "The objective for the agent"
}
}
}Output Schema
{
"type": "object",
"properties": {
"done": {
"type": "boolean"
},
"result": {
"type": "object"
}
}
}Permissions
Declared by the publisher. Checked before execution by the policy gate.
Permissions are policy-checked before execution. Network and filesystem access are not sandboxed at runtime. Learn more
Privacy
All tool execution happens locally on your machine. AgentNode never receives:
- • Tool inputs or outputs
- • Execution logs
- • Data your agent processes
Only install events and search queries are sent to the registry.
agentnode install code-review-agentFiles (4)
License
MITStats
Compatibility
Frameworks
Runtime
pythonPython Version
>=3.10Trust & Security
Publisher
AgentNode
@agentnode