
Developer Cole Medin has open-sourced a collection of prompt-based 'skills' designed to orchestrate coding agents like Claude Code and Codex. The toolkit, available under the MIT license on GitHub, includes specific modules for requirements analysis, specification writing, task slicing, and code validation. Medin demonstrates these tools in real enterprise training scenarios, emphasizing a structured loop where planning precedes implementation. The release aims to standardize agentic workflows by providing minimalistic, installable configurations that users can adapt to existing projects.
Read originalThis release stabilizes the core agent loop by fixing critical bugs in prompt caching and subagent resume logic that previously broke context reuse. Plugin management gets a significant upgrade with dynamic folder scanning, allowing developers to hot-load tools without restarting the session. The update also hardens security around symlink traversal and refines telemetry routing for enterprise gateways. While not feature-heavy, these fixes make Claude Code more reliable for complex, multi-step coding workflows.
Anthropic quietly patched a regression in Claude Code that broke LLM-gateway and proxy setups. The previous version incorrectly forced Cloud-gateway sign-in when the CLAUDE_CODE_USE_GATEWAY variable was set, even with API keys or custom auth headers configured. This update restores the expected behavior where the variable is ignored unless specific Anthropic credentials are present. Developers relying on custom authentication flows can now resume their workflows without configuration changes.