Agentic Jujutsu
Skill Verified ActiveQuantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
To enable AI agents to collaborate effectively on code and tasks, learn from their interactions, and maintain a secure, version-controlled history of operations.
Features
- Quantum-resistant, self-learning version control
- Multi-agent coordination and collaboration
- ReasoningBank intelligence for pattern discovery
- Automated conflict resolution and suggestions
- Federated communication with zero-trust security
- Vector memory with fast retrieval (AgentDB)
- Comprehensive CLI and plugin-based installation
Use Cases
- Coordinating multiple AI agents modifying code simultaneously
- Implementing lock-free version control for faster workflows
- Enabling AI agents to learn from past successes and improve performance
- Securing AI agent communications with quantum-resistant cryptography
- Building complex, multi-agent systems that require coordinated task execution
Non-Goals
- Replacing standard version control systems like Git for human developers
- Providing a generic LLM interface without specific agentic capabilities
- Handling non-AI agent workflows or traditional software development tasks directly
Workflow
- Initialize Agentic Jujutsu wrapper
- Start a learning trajectory with a task description
- Perform agent operations (e.g., status, commit, branch create)
- Add operations to the trajectory
- Finalize the trajectory with a success score and critique
- Utilize learned patterns for suggestions and coordination
Practices
- AI Agent Coordination
- Self-Learning Systems
- Secure Agent Communication
- Version Control for AI
Prerequisites
- Node.js (for CLI installation)
- Claude Code environment (for plugin usage)
Scope
- info:Tool surface sizeThe extension exposes a large number of tools and commands across its various plugins, which is necessary for its broad functionality but could potentially be overwhelming.
Installation
npx skills add ruvnet/rufloRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Ralplan
99Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution
Lean Ctx
100Context Runtime for AI Agents — 59 MCP tools, 10 read modes, 95+ shell patterns, tree-sitter AST for 18 languages. Compresses LLM context by up to 99%. Use when reading files, running shell commands, searching code, or exploring directories. Auto-installs if not present.
Manus
100Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.
Risk Management
100Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt", "position size", "lot size", "confidence", "revenge trading", "overtrading", "discipline".
Setup Gbrain
100Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)
Skill Creator
100Guide for creating effective skills