gmickel-claude-marketplace and claude-night-market

These are complements: gmickel's Flow-Next and Ralph provide planning/execution workflows that would integrate with athola's production-ready plugins and multi-LLM delegation to create a complete plan-first autonomous coding system.

claude-night-market
50
Established
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 14/25
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 14/25
Stars: 545
Forks: 37
Downloads:
Commits (30d): 5
Language: Python
License: MIT
Stars: 219
Forks: 21
Downloads:
Commits (30d): 0
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About gmickel-claude-marketplace

gmickel/gmickel-claude-marketplace

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.

Implements re-anchoring—re-reading specs and git state before every task—to combat context drift within Claude's token limits, using fresh context per task iteration. Supports cross-model review gates via RepoPrompt or Codex CLI, enabling multi-agent validation across different LLM backends. Ralph autonomous mode runs iteratively overnight with receipt-based gating and auto-blocking for stuck tasks, while dependency graphs enforce task ordering and multi-user safety via scan-based IDs without requiring a coordination server.

About claude-night-market

athola/claude-night-market

17 production-ready Claude Code plugins: git workflows, code review, spec-driven development, architecture patterns, resource optimization, and multi-LLM delegation. 130 skills, 103 commands, 43 agents.

Organized as a four-layer dependency hierarchy, the 19 plugins use Claude Code's hook system (PreToolUse gates) for governance—enforcing TDD, blocking unsafe operations, and auto-escalating high-risk tasks to human review. State persists across sessions via task lists and GitHub Discussions, while `egregore` orchestrates autonomous agents with parallel worktree isolation, agent specialization, and watchdog-based crash recovery.

Scores updated daily from GitHub, PyPI, and npm data. How scores work