By gmickel
Run AI-driven two-step workflows to generate structured plans from feature requests or bugs, perform rigorous Carmack-level plan and code reviews using repo context, then execute end-to-end: git worktree/branch setup, phased task tracking, quality audits, tests, commits, and PR reviews.
npx claudepluginhub gmickel/flow-next --plugin flowJohn Carmack-level implementation review via rp-cli (current branch changes)
Interview & refine a bead or spec file in-depth
Carmack-level plan review via rp-cli context builder + chat
Draft a clear build plan from a short request
Execute a plan file end-to-end with checks
Token-efficient codebase exploration using RepoPrompt codemaps and slices. Use when you need deep codebase understanding without bloating context.
Find the most relevant framework/library docs for the requested change.
Map user flows, edge cases, and missing requirements from a brief spec.
Gather modern best practices and pitfalls for the requested change.
Review recent changes for correctness, simplicity, security, and test coverage.
Scan repo to find existing patterns, conventions, and related code paths for a requested change.
John Carmack-level implementation review via rp-cli for current branch changes. Use when reviewing code changes, PRs, or implementations. Triggers on mentions of code review, implementation review, or PR review.
Interview user in-depth about a spec, bead, or feature idea to extract complete implementation details. Use when user wants to flesh out a spec, refine requirements, discuss technical details, clarify a feature before building, or asks to be interviewed about their idea. Triggers on "interview me", "ask me questions about", "flesh out this spec", "refine requirements", "help me think through".
Carmack-level plan review via rp-cli context builder + chat. Use when reviewing implementation plans, architecture docs, or design specs. Triggers on mentions of plan review, design review, or architecture review.
Create structured build plans from feature requests, bug reports, or Beads issue IDs. Use when planning features, designing implementation, preparing work breakdown, or when given a bead/issue ID to plan. Triggers on /flow:plan with text descriptions or issue IDs (e.g., bd-123, gno-45, app-12).
Execute a plan file or Beads epic systematically with git setup, task tracking, quality checks, and commit workflow. Use when implementing a plan, working through a spec, following documented steps, or executing a Beads issue ID (e.g., bd-123, gno-45, app-12).
Token-efficient codebase exploration using RepoPrompt CLI. Use when user says "use rp to..." or "use repoprompt to..." followed by explore, find, understand, search, or similar actions.
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
💬 Join the Discord — discussions, updates, feature requests, bug reports
Flow-Next is an AI agent orchestration plugin. Bundled task tracking, dependency graphs, re-anchoring, and cross-model reviews. Everything lives in your repo — no external services, no global config. Uninstall: delete .flow/.
Works on Claude Code, OpenAI Codex (CLI + Desktop), Factory Droid, and OpenCode.
| Claude Code | OpenAI Codex | Factory Droid |
|
|
|
Update Codex: cd flow-next && git pull, then /plugins → uninstall → install.
📖 Full docs · Codex install guide · OpenCode port
| Problem | Solution |
|---|---|
| Context drift | Re-anchoring before every task — re-reads specs + git state |
| Context window limits | Fresh context per task — worker subagent starts clean |
| Single-model blind spots | Cross-model reviews — RepoPrompt or Codex as second opinion |
| Forgotten requirements | Dependency graphs — tasks declare blockers, run in order |
| "It worked on my machine" | Evidence recording — commits, tests, PRs tracked per task |
| Infinite retry loops | Auto-block stuck tasks — fails after N attempts, moves on |
| Duplicate implementations | Pre-implementation search — worker checks for similar code before writing new |
| Command | What It Does |
|---|---|
/flow-next:plan | Research codebase, create epic + tasks |
/flow-next:work | Execute tasks with re-anchoring |
/flow-next:interview | Deep spec refinement (40+ questions) |
/flow-next:impl-review | Cross-model implementation review |
/flow-next:plan-review | Cross-model plan review |
/flow-next:epic-review | Epic-completion review gate |
/flow-next:prime | Assess codebase agent-readiness |
/flow-next:ralph-init | Scaffold autonomous loop |
Run overnight. Fresh context per iteration + multi-model review gates + auto-block stuck tasks.
/flow-next:ralph-init # One-time setup
scripts/ralph/ralph.sh # Run from terminal
📖 Ralph deep dive · Ralph TUI (bun add -g @gmickel/flow-next-tui)
| Project | Platform |
|---|---|
| flow-next-opencode | OpenCode |
| FlowFactory | Factory.ai Droid |
GNO — Local hybrid search for your notes, docs, and code. Give Claude Code long-term memory over your files via MCP.
bun install -g @gmickel/gno && gno mcp install --target claude-code
Made by Gordon Mickel · @gmickel · gordon@mickel.tech
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, rules, and legacy command shims evolved over 10+ months of intensive daily use
Uses power tools
Uses Bash, Write, or Edit tools
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Works with Claude Code, Kiro, Clawd CLI, Gemini CLI, Cursor, Continue, Hermes, and 17+ AI coding assistants. Now with Arabic, German, Spanish, and Chinese (Simplified & Traditional) support.
Context-Driven Development plugin that transforms Claude Code into a project management tool with structured workflow: Context → Spec & Plan → Implement
AI-supervised issue tracker for coding workflows. Manage tasks, discover work, and maintain context with simple CLI commands.
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.