sre-ai-rules
01Cursor rule Cursor
SmythOS SRE Monorepo AI Development Guidelines.
Cursor rule Cursor
SmythOS SRE Monorepo AI Development Guidelines.
Agent
The SmythOS SDK offers flexible ways to create and configure agents. This guide covers everything from basic agent creation to advanced model configuration.
Agent
Skills are the building blocks that give agents their capabilities. Each skill is a function that the agent's LLM can decide to call based on the user's prompt.
Agent
Agent modes are pluggable execution strategies that augment how an agent processes and responds to tasks. Each mode adds specialized capabilities through additional behavior (system prompt) instructions and hidden skills, all managed transparently by the SDK.
Agent
Planner mode gives an agent systematic planning capabilities. When the agent receives a complex or multi-step task, it will create a structured plan, track each step's progress, and verify completion before finishing.
Agent
Worker mode allows an agent to dispatch complex, long-running tasks to background "copy" agents while the main agent stays fully interactive. When a worker finishes, its result is automatically surfaced back to the user through the main agent's conversation.
Cursor rule Cursor
It is critically important that you adhere to the above five rules.
Instructions file
Claude Code instructions for SmythOS/smyth-docs, covering claude.md, project overview, commands, architecture and content (docs/).