gmickel-claude-marketplace and claude-swe-workflows

These are ecosystem siblings—one provides a comprehensive workflow framework (Flow-Next, Ralph autonomous mode, multi-model review gates) while the other appears to be a mirror/alternative implementation of Claude Code plugins for similar software engineering tasks, both occupying the same tool category without direct integration or substitution.

gmickel-claude-marketplace
50
Established
claude-swe-workflows
39
Emerging
Maintenance 13/25
Adoption 10/25
Maturity 13/25
Community 14/25
Maintenance 13/25
Adoption 4/25
Maturity 9/25
Community 13/25
Stars: 545
Forks: 37
Downloads: —
Commits (30d): 5
Language: Python
License: MIT
Stars: 7
Forks: 2
Downloads: —
Commits (30d): 0
Language: Makefile
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-swe-workflows

chrisallenlane/claude-swe-workflows

Personal Claude Code plugins (MIRROR)

Composable, multi-layered workflows for Claude Code that scale from single-ticket implementation to full-project orchestration with integrated planning, quality gates, and autonomous agent coordination. Each workflow layer—from `/implement` (single ticket) through `/implement-batch` and `/implement-project`—dispatches to language-specific specialists, runs QA verification and code review, then executes quality passes (refactoring, architecture review, test/doc audits). Planning workflows (`/scope`, `/scope-project`) use adversarial review to validate tickets before implementation, with supporting utilities for bug diagnosis, deliberation, and pre-release checks.

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-plugins gmickel-claude-marketplace and claude-code-supervisor

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