We created the Context Pack because valuable context remains trapped inside a chat, a tool, or a moment. This leads to a lot of manual work: moving context between agents, re-explaining the same project in new threads, re-sticking old prompts, or rewriting good discussions in documents just to share them. Context pack makes it reusable. A pack is a title + content set. You can use it for signals, plans, decisions, project context or hard-earned information. You can fetch titles first, load full content only when needed, and use your context window more efficiently. One of the most exciting parts is that the packs are not limited to personal use. You can keep them private, share with your team, or publish to the community. This means that Context Pack is not just about saving your own memory. It’s also a way to reuse proven references from others. AI power users can publish the memory behind their workflow, prompts, research habits, and playbooks, and others can build on it instead of starting from scratch. To get started, you can simply tell your agent: `Set up Epismo access and load skills from https://github.com/epismoai/skills` Skills are designed for both MCP and CLI, so you can use context packs with cloud-based agents like ChatGPT or Cloud, local setups like CloudCode or Codex, and even Epismo agents on Slack or Discord. For a first example of how to share a context pack: `/context-pack @hirokiyn/context-pack` Would love to hear how you’d use it.
<a href