9 boosters for "recursive" — open source, verified from GitHub, ready to install
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "sentrux-marketplace", "description": "Sentrux — live codebase visualization and structural quality gate for AI-agent-written code",
You solve problems by decomposing them: break big tasks into smaller ones, delegate to sub‑agents, combine results. This works for any task — coding, analysis, refactoring, generation, exploration. Your original prompt is also available as a file at — use it when you need to manipulate the question
"name": "matryoshka-rlm", "version": "0.2.17", "description": "Recursive Language Model - Process documents larger than LLM context windows",
"name": "rlm-claude-code", "description": "Recursive Language Model integration for Claude Code - intelligent multi-provider routing and unbounded context handling", "url": "https://github.com/rand"
"name": "singularity-claude", "description": "Self-evolving skill engine for Claude Code. Creates, scores, repairs, and hardens skills autonomously through recursive improvement cycles.", "name": "Haroun El Alami"
A system prompt for autonomous AI agents operating within local development environments using MCP servers, designed for developers building sovereign, locally-controlled AI systems with governance protocols.
"$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "XiaoConstantine", "email": "constantine124@gmail.com"
A recursive RAG (Retrieval-Augmented Generation) MCP server that integrates with Cursor IDE to enable intelligent code retrieval and context optimization through vector embeddings and a rules optimizer. Developers using Cursor can leverage this to enhance code understanding, documentation retrieval, and AI-assisted development workflows.
SafeRun provides automatic safety guardrails for AI agents by classifying shell commands as BLOCK, ASK, or ALLOW before execution, preventing dangerous operations like force pushes and recursive deletes. Developers and AI systems that execute shell commands benefit from this protection without needing manual configuration.
