by gmickel
Claude Code plugins for reliable AI coding. Flow-Next: plan-first workflows, Ralph autonomous mode (overnight coding with fresh context), multi-model review gates via RepoPrompt/Codex, re-anchoring to prevent drift, receipt-based gating.
# Add to your Claude Code skills
git clone https://github.com/gmickel/gmickel-claude-marketplacePlugins that make AI agents actually work.
π¬ Join the Discord β discussions, updates, feature requests, bug reports
π Update issues? Run:
claude plugin update flow-next@gmickel-claude-marketplaceπ /flow-next:epic-review: Epic-completion review gate. Catches requirement gaps that per-task reviews missβbefore epic closes.
π€ Ralph mode: Ship features while you sleep. Fresh context per iteration, multi-model review gates, auto-blocks stuck tasks.
π‘ Cross-platform reviews: (macOS) or (any OS) Β·
No comments yet. Be the first to share your thoughts!
π§ͺ OpenCode user? Try flow-next-opencode (experimental port)
[!TIP] π€ Works on Factory Droid too! Claude Code plugins are fully compatible:
droid plugin marketplace add https://github.com/gmickel/gmickel-claude-marketplaceThen
/pluginsβ Marketplace β install flow-next. Commands don't autocomplete yet but work when typed (e.g./flow-next:plan). Skills load automatically.
[!TIP] π₯οΈ OpenAI Codex user? Full multi-agent support (20 roles, parallel scouts, 3-tier model mapping):
git clone https://github.com/gmickel/gmickel-claude-marketplace.git cd gmickel-claude-marketplace && ./scripts/install-codex.sh flow-nextRequires Codex 0.102.0+. Commands use
/prompts:prefix (e.g./prompts:plan). See Codex install guide.
Process failures, not model failures:
This marketplace ships plugins that fix these problems.
Plan first, work second. Zero external dependencies.
# Install
/plugin marketplace add https://github.com/gmickel/gmickel-claude-marketplace
/plugin install flow-next
# Setup (configures review backend + CLI tools)
/flow-next:setup
# Use
/flow-next:plan Add a contact form with validation
/flow-next:work fn-1
| Problem | Solution |
|---------|----------|
| Context drift | Re-anchoring before EVERY task β re-reads specs + git state from .flow/ |
| 200K token limits | Fresh context per task β worker subagent starts clean each task |
| Single-model blind spots | Cross-model reviews β RepoPrompt or Codex as second opinion |
| Forgotten requirements | Dependency graphs β tasks declare blockers, nothing runs out of order |
| "It worked on my machine" | Evidence recording β commits, test output, PRs tracked per task |
| Infinite retry loops | Auto-block stuck tasks β fails after N attempts, moves on |
| Team conflicts | Multi-user safe β scan-based IDs, soft claims, no coordination server |
| 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:plan-review | Cross-model plan review |
| /flow-next:impl-review | Cross-model implementation review |
| /flow-next:prime | Assess codebase agent-readiness, propose fixes |
| /flow-next:ralph-init | Scaffold autonomous loop |
π Full documentation β CLI reference, workflow details, troubleshooting
π€ Confused when to use Interview vs Plan vs Work? See When to Use What
Run overnight, walk away. Fresh context per iteration + multi-model review gates.
/flow-next:ralph-init # One-time setup
scripts/ralph/ralph.sh # Run from terminal
How Ralph differs:
| Aspect | Typical Agents | Ralph | |--------|---------------|-------| | Context | Accumulates (drift) | Fresh each iteration | | Review | Self-review only | Cross-model gates | | Stuck tasks | Infinite retry | Auto-block after N failures | | Validation | Tests only | Tests + receipts + reviews |
π Ralph deep dive β guard hooks, receipt gating, sentinel controls
π₯οΈ Ralph TUI β Terminal UI for monitoring (bun add -g @gmickel/flow-next-tui)
# Add marketplace
/plugin marketplace add https://github.com/gmickel/gmickel-claude-marketplace
# Install flow-next
/plugin install flow-next
# Setup (configures review backend + CLI tools)
/flow-next:setup
| Plugin | Status | |--------|--------| | flow-next | Active development. Recommended. | | flow | Legacy. Documentation |
| Project | Platform | |---------|----------| | flow-next-opencode | OpenCode | | FlowFactory | Factory.ai Droid |
GNO β 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
plugins/<name>/ with .claude-plugin/plugin.json.claude-plugin/marketplace.jsonjq . .claude-plugin/marketplace.jsonMade by Gordon Mickel Β· @gmickel Β· gordon@mickel.tech