ChatGPT Reviewer — Project Management agent for Claude Code
Use when the main thread wants a second opinion on a change from ChatGPT without spending its own context reading the diff — forwards a review or planning task to the ChatGPT bridge and returns the re.
How to install ChatGPT Reviewer
Installs to ~/.claude/agents/nguyengiatam-chatgpt-agent-chatgpt-reviewer.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/nguyengiatam/chatgpt-agent/HEAD/agents/chatgpt-reviewer.md -o ~/.claude/agents/nguyengiatam-chatgpt-agent-chatgpt-reviewer.md Restart Claude Code, or start a new session, for it to be picked up.
What ChatGPT Reviewer does
name: chatgpt-reviewer description: Use when the main thread wants a second opinion on a change from ChatGPT without spending its own context reading the diff — forwards a review or planning task to the ChatGPT bridge and returns the result model: haiku tools: Bash skills:
- chatgpt-agent-runtime
You are a forwarding wrapper around the ChatGPT bridge. You do not review anything yourself and you do not read the repository.
Forwarding rules:
- Make exactly one
Bashcall: `python3
Alternatives in Project Management
- Agent Evaluator — Evaluates agent output against 5-axis quality rubric (accuracy, completeness, clarity, actionability, concisen 243.5k ★
- Flow Git — Use this agent for git operations — atomic commits, rebase, history cleanup, and style detection 523 ★
- Change Verifier — Use this agent after every change to the codebase to verify the project still lints, type-checks, tests, and b 204 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Paper Analyst
Read-only research analyst — deep-reads ONE arXiv paper's LaTeX source and returns a typed relevance verdict a
Bfl Node Reviewer
Independent second-opinion diff reviewer for ComfyUI-FLUX-BFL-API. Loads BFL invariants into fresh context and
Arthur
Independent code review via the Codex CLI (read-only, headless) for a second opinion that reads project files
Mp Adversarial Reviewer
Adversarial second-opinion review of a completed masterplan task. The harness runs this agent on the routing p
Envoy Runner
Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper roo
Background Task Manager
Manages background tasks for code analysis and monitoring without blocking main workflow
Related Skills
Dsh Auto Review
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns stru
UX Critique
Open-ended taste call on a specific surface. Not a structured audit — a designer's opinion. Returns 3 wins, 3
Second Opinion
Trail of Bits security skill for second opinion