Claude Opus 5.5 just got its internals opened.
This is a dev post classified by Jev as AI dev tools (a tool drop), kept by the Dev Radar because it carries real work, not commentary.
Claude Opus 5.5 just got its internals opened. full system-prompt extract: 1.9M+ characters, including tools, How Claude decides when to delegate to another agent What stands out: - Subagent launching for multi-step work. - Isolated git worktrees - Private HTML artifacts - Memory + privacy constraints - A very detailed agent harness This is more “operating system for an AI coworker.” Useful reading for researchers, builders, and anyone following agent design. - http://github.com/elder-plinius/CL4R1T4S/blob/main/ANTHROPIC/CLAUDE-OPUS-5.5.md
Posted by Md Ismail Šojal 🕷️ (56k followers) 1 h ago · 1 likes · 529 views · view the original post on X. Kept by the Dev Radar as AI dev tools. Tools mentioned: cl4r1t4s.
More dev work like this
- 81% of teams have agents in testing or live use, while only 14% have full security… — @TryArcade
- Browser control is useful. Agent-specific setup is the drag. — @DanKornas
- GPT-6 Luna is live on Concentrate. — @concentrateai
- AI Usage Dashboard for Omarchy v1.6.0 is out. — @btsouth
- Grok 4.7 is live on Concentrate. — @concentrateai
- GPT-6 Sol and GPT-6 Luna are now available in Visual Studio. — @VisualStudio
- Great prompt from Anthropic. — @omarsar0
- oh wow... One Shot with Claude Opus 5.5. — @agentnative_
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 21.5k posts from 5k X accounts over the last 21 days, 2.5k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-22 21:38 UTC. Full method.