gmickel-claude-marketplace and claude-plugins

These are **complements** — both implement plan-first SDLC workflows with multi-model review gates for Claude code generation, but A focuses on autonomous overnight coding with context re-anchoring while B emphasizes self-learning grounded in your codebase, making them suitable for use together in a layered coding pipeline.

gmickel-claude-marketplace
50
Established
claude-plugins
39
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 14/25
Maintenance 13/25
Adoption 9/25
Maturity 11/25
Community 6/25
Stars: 545
Forks: 37
Downloads: —
Commits (30d): 5
Language: Python
License: MIT
Stars: 71
Forks: 3
Downloads: —
Commits (30d): 0
Language: Python
License: Apache-2.0
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-plugins

closedloop-ai/claude-plugins

Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase. Bootstrap, Plan, & Ship.

Implements a multi-agent orchestration framework atop Claude Code via six specialized plugins (bootstrap, code generation, code-review, quality judges, platform guidance, and self-learning) that gate workflow phases until correctness criteria are met. Uses codebase-grounded execution with adaptive feedback loops to reduce hallucinations and cost—benchmarks show performance parity with Claude Opus 4.6 at 50% expense. Designed for Claude Code integration; requires Python 3.11+ and ships with artifact-bound phased gates, multi-repository support, and organizational pattern capture for knowledge reuse across teams.

Related comparisons

gmickel-claude-marketplace and claude-code-plugins-plus-skills gmickel-claude-marketplace and claude-code-skills gmickel-claude-marketplace and claude-night-market gmickel-claude-marketplace and ai-coding-config gmickel-claude-marketplace and claude-swe-workflows gmickel-claude-marketplace and claude-code-supervisor

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