claude-code-plugins-plus-skills and gmickel-claude-marketplace

These are ecosystem siblings—one provides a broad plugin marketplace and package management infrastructure (A), while the other builds specialized workflow patterns and autonomous coding modes (B) that could run on top of that foundation.

claude-code-plugins-plus-skills
69
Established
gmickel-claude-marketplace
50
Established
Maintenance 25/25
Adoption 10/25
Maturity 13/25
Community 21/25
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 14/25
Stars: 1,602
Forks: 194
Downloads: —
Commits (30d): 335
Language: Python
License: —
Stars: 545
Forks: 37
Downloads: —
Commits (30d): 5
Language: Python
License: MIT
No Package No Dependents
No Package No Dependents

About claude-code-plugins-plus-skills

jeremylongshore/claude-code-plugins-plus-skills

340 plugins + 1367 agent skills for Claude Code. Open-source marketplace with CCPI package manager, interactive tutorials, and production orchestration patterns.

Plugins activate through frontmatter-based trigger phrases in markdown SKILL.md files, allowing Claude Code to automatically invoke relevant tasks without explicit slash commands. The marketplace supports three plugin types—AI instruction plugins (markdown-only), MCP Server plugins (Node.js processes via Model Context Protocol), and SaaS skill packs for platforms like Deepgram and Linear—managed through the CCPI CLI or Claude's native `/plugin` commands. Includes production orchestration patterns and learning labs documenting multi-agent workflow architecture with empirical validation guides.

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.

Related comparisons

claude-code-plugins-plus-skills and claude-code-skills claude-code-plugins-plus-skills and miyabi-claude-plugins claude-code-plugins-plus-skills and claude-night-market claude-code-plugins-plus-skills and ai-coding-config claude-code-plugins-plus-skills and luxor-claude-marketplace claude-code-plugins-plus-skills and claude-plugins

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