claude-prompts and systemprompt-code-orchestrator

These are complements: the prompt template server provides reusable thinking frameworks and quality gates that would enhance the code orchestration agent's decision-making and output validation during task execution.

claude-prompts
61
Established
Maintenance 13/25
Adoption 10/25
Maturity 18/25
Community 20/25
Maintenance 2/25
Adoption 10/25
Maturity 9/25
Community 20/25
Stars: 141
Forks: 29
Downloads:
Commits (30d): 0
Language: TypeScript
License: AGPL-3.0
Stars: 139
Forks: 28
Downloads:
Commits (30d): 0
Language: TypeScript
License: MIT
No risk flags
Stale 6m No Package No Dependents

About claude-prompts

minipuft/claude-prompts

MCP prompt template server: hot-reload, thinking frameworks, quality gates

Implements multi-step agentic workflows using composable operator syntax with mid-chain context threading and agent handoff capabilities. Built as an MCP server with YAML-based prompt templates that support validation gates, self-evaluation hooks, and shell command execution for output verification. Exports workflows as client-native skills and integrates with Claude Desktop, VS Code, Cursor, OpenCode, and Gemini CLI via stdio transport with client-specific presets for deterministic guidance.

About systemprompt-code-orchestrator

systempromptio/systemprompt-code-orchestrator

MCP server for orchestrating AI coding agents (Claude Code CLI & Gemini CLI). Features task management, process execution, Git integration, and dynamic resource discovery. Full TypeScript implementation with Docker support and Cloudflare Tunnel integration.

Implements a real-time resource subscription model using MCP's `listChanged` notifications for live task monitoring, eliminating the need for polling between clients and server. Features stateful process management with disk-persisted JSON task storage, Firebase Cloud Messaging for push notifications on task completion, and a host bridge daemon that routes commands between Docker containers and the local machine—enabling AI agents to execute with full filesystem access while keeping code local.

Related comparisons

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