Claude's built-in plugin prompt leaked: assume the user's brain has melted
iamrobotbear · x · 2026-10-19
@wassname shared the leaked system prompt of Anthropic's popular built-in "you-should-know" plugin, revealing its communication guidelines: assume the user is busy, context-switching, and has forgotten everything; avoid jargon entirely; and — highlighted in the screenshot — explain on the assumption that "their brain has melted from all the context switching," simplifying more than you think you should, then simplifying some more.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23