跳到正文
FunCoding

搜索

搜索文档、文章、Skill 和 MCP

Context Engineering

Provide goose with the knowledge, preferences, and workflows it needs to work effectively

Context Engineering

Context engineering is about building background knowledge, preferences, and workflows that help goose work more effectively. Instead of repeating instructions, you define them once and teach goose how you work.

📚 Documentation & Guides

- [Using goosehints](/agents/goose/guides/context-engineering/using-goosehints/):Use AGENTS.md, .goosehints, and other files to provide project context, preferences, and instructions that goose loads automatically. - [Using Skills](/agents/goose/guides/context-engineering/using-skills/):Create reusable instruction sets containing workflows, scripts, and other resources that goose can load on demand. - [Custom Agents](/agents/goose/guides/context-engineering/custom-agents/):Create, edit, import, and export specialized goose agents with reusable prompts and optional metadata. - [Plugins](/agents/goose/guides/context-engineering/plugins/):Install, update, and manage packages that extend goose with skills, hooks, and other reusable components. - [Hooks](/agents/goose/guides/context-engineering/hooks/):Run scripts when goose starts sessions, submits prompts, calls tools, edits files, or executes shell commands. - [Custom Slash Commands](/agents/goose/guides/context-engineering/slash-commands/):Create custom shortcuts to quickly run reusable instructions in any chat session with simple slash commands. - [Prompt Templates](/agents/goose/guides/context-engineering/prompt-templates/):Customize the built-in prompts that define how goose responds, plans, compacts context, and creates recipes. - [Subagents](/agents/goose/guides/context-engineering/subagents/):Delegate focused tasks to isolated goose instances that can run sequentially or in parallel. - [Persistent Instructions](/agents/goose/guides/context-engineering/using-persistent-instructions/):Inject critical reminders into goose's working memory every turn. Ideal for security guardrails and behavioral rules that must never be forgotten. - [Memory Extension](/agents/goose/mcp/memory-mcp/):Teach goose persistent knowledge it can recall across sessions. Save commands, code snippets, and preferences for consistent assistance. - [Research → Plan → Implement Pattern](/agents/goose/tutorials/rpi/):See how slash commands make it easy to integrate instructions into interactive RPI workflows.
- [What's in my .goosehints file](https://goose-docs.ai/blog/2025/06/05/whats-in-my-goosehints-file):A deep dive into .goosehints vs Memory Extension, and how to optimize your goose configuration for better performance. - [Stop Your AI Agent From Making Unwanted Changes](https://goose-docs.ai/blog/2025/12/10/stop-ai-agent-unwanted-changes):Teach your AI agent how to commit early and often so you can control changes and roll back safely. - [The AI Skeptic's Guide to Context Windows](https://goose-docs.ai/blog/2025/08/18/understanding-context-windows):Why do AI agents forget? Learn how context windows, tokens, and goose help you manage memory and long conversations. - [Hooks: run your own scripts on every goose event](https://goose-docs.ai/blog/2026/05/14/goose-hooks):Learn how lifecycle hooks let you react to session, prompt, tool, file, and shell events with your own scripts.