ChatGPT Plan Review — Development agent for Claude Code
ChatGPT implementation-plan review targeting tasks/builds/{slug}/plan.md; manual / automated / parallel modes, hard-default manual.
How to install ChatGPT Plan Review
Installs to ~/.claude/agents/michaelhazza-claude-code-framework-chatgpt-plan-review.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/michaelhazza/claude-code-framework/HEAD/.claude/agents/chatgpt-plan-review.md -o ~/.claude/agents/michaelhazza-claude-code-framework-chatgpt-plan-review.md Restart Claude Code, or start a new session, for it to be picked up.
What ChatGPT Plan Review does
name: chatgpt-plan-review description: "ChatGPT implementation-plan review targeting tasks/builds/{slug}/plan.md; manual / automated / parallel modes, hard-default manual. Triages technical (auto-applied) vs user-facing (operator-approved) findings. Dispatched by feature-coordinator Step 4; not invoked directly." tools: Read, Glob, Grep, Bash, Edit, Write model: opus
**Project context (read first).** If `.claude/context/agent-context.md` exists, consume it with bounded reads in this exa
Alternatives in Development
- Claude Code Hook Comms (hcom) — by aannoo - Lightweight CLI tool for real-time communication between Claude Code sub agents using hooks 155 ★
- Learn Review — Analyzes diffs between generated prose and manual edits to identify patterns for sharpening registers, skill r 70 ★
- Media Buyer — Invoke when the user needs help with paid advertising — campaign setup, audience targeting, bid strategies, ad 64 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
ChatGPT PR Review
Coordinates ChatGPT PR review round-by-round in a dedicated session (manual / automated / parallel modes). Rea
Incident Scribe
When a workflow fails 3+ times in same session or a prod/client-facing issue happens, writes a structured inci
Parse Memory
Step agent that parses input into a chunk manifest for memory storage. Handles both manual triggers (remember
Bid Strategy Smart Bidding Governance Subagent
Cross-cutting sub-agent owning bid-strategy fit and automated/Smart Bidding governance across every auction-ba
Resolve Issue
Resolve a GitHub issue end-to-end. Supports modes: auto (no stops), manual (artifacts only). Trigger on: resol
Dnp Fable Advisor
🧠 Senior .NET advisor to the implementation agents — advises, never implements. Three modes via brief: ADVISE
Related Skills
Spray
Password spray with hard guards — typed-hostname confirmation, lockout warning, audit log. Modes: http-form (c
Nexscope Plugin
Lets multiple AI coding agents (Claude Code, Codex CLI) and humans share a single chat room over a WebSocket r
Luck
A skill for improving the luck of your AI stack and projects—developed from an applied theoretical framework.