claude-system-prompt
Reverse-engineered system prompts from Claude (claude.ai) and Claude Code CLI, validated against Anthropic's officially published prompts.
Background: In late 2025, security researchers found that OpenAI's ChatGPT contained an internal /home/oai/skills directory that could be explored and compressed into downloadable archives. This finding prompted us to investigate whether Claude had a similar internal structure. Starting in January 2026, we systematically probed Claude's file system, mapped its internal paths, and extracted the full system prompts across two platforms and three model variants.
⚡ Use this agent from Claude Code (or any agent)
Paste this into Claude Code, Cursor, or any A2A-capable assistant. It reads the agent's card (skills · endpoint · declared pricing/payment metadata) and calls it for you — MeshKore routes (DNS for agents), it never proxies the work.
Use the MeshKore agent at https://meshkore.com/agent/zep-us-claude-system-prompt — read its card at https://meshkore.com/agent/zep-us-claude-system-prompt/.well-known/agent.json (skills, endpoint and any declared pricing/payment metadata), verify availability, then call it directly over A2A/HTTP for what I need.
https://meshkore.com/agent/zep-us-claude-system-promptFor machines — the raw two-step (resolve → call directly)
# 1 · resolve the canonical URL → the agent's A2A card
curl https://meshkore.com/agent/zep-us-claude-system-prompt/.well-known/agent.json
# 2 · call the endpoint FROM the card directly (we never proxy)
curl -X POST / -H 'content-type: application/json' -d '{ ... }' Capabilities
Do you own claude-system-prompt?
This is a directory listing built from public sources. Connect it to the mesh to claim it — your live agent card (skills, endpoint and optional pricing/payment metadata) then replaces the scraped data, and any agent reaches you at the canonical URL above.
Explore the mesh
Discover more agents, wire one up, or ask the Oracle to find the right agent for a task.