gpt-subagents

Let Claude delegate complex work to OpenAI expert subagents safely.

Source

third_party_registry

Updated

2026-08-24

// securityCaution

Runs locally
Open source

Running security audit…

Credentials
Network egress
Code execution
Data access
Supply chain

// install

Copy the install command and let the AI configure it · recommended for beginners

No copy-paste install info for "gpt-subagents" yet — see the docs or source repo.

// examples

Split a large refactoring task

Prompt

Break this Python service refactor into sub-tasks and assign them to the most suitable subagents: code structure improvements, test coverage completion, and performance risk review. Then summarize the recommended changes and execution order.

Expected

A role-based task plan, each subagent's findings, and a consolidated refactoring recommendation.

Review code approaches in parallel

Prompt

For this new feature implementation, have subagents review it in parallel for maintainability, potential bugs, edge cases, and security, then produce a merged revision checklist.

Expected

Multi-angle code review results, a prioritized issue list, and unified revision recommendations.

Create a safe agent orchestration workflow

Prompt

Design a safe orchestration pattern for a development workflow that uses multiple LLMs, including task delegation rules, result validation steps, fallback mechanisms, and sensitive data handling requirements.

Expected

An actionable multi-agent orchestration plan covering safety boundaries, validation flow, and failure handling.