Official @ClaudeDevs: Claude Code adds `claude plugin eval`—author test cases, score a plugin/skill against a no-plugin baseline (terminal + HTML), then `claude update`. Docs at code.claude.com/docs/en/plugin-evals. Evals burn tokens; MCP/hooks run as configured.
AI Research
Apply to your dev workflow or calculate costs
The unofficial-but-tolerated Claude Code Changelog bot (@ClaudeCodeLog) posted 2.1.274 with 108 CLI changes. Highlights: a visible critical-memory warning with safe free/restart steps; sessions no longer loop forever on unexpected tool_use_id 400s (transcripts self-heal when possible, else a clear /rewind error ends the loop); MCP 403 insufficient_scope now names missing permissions and points to /mcp re-auth; CLAUDE_CODE_MCP_STARTUP_WAIT_MS bounds how long the first non-interactive turn waits for MCP servers. Many more MCP/stream, /goal resume, self-hosted runner 401, VS Code, and cloud session/routine fixes. Source: anthropics/claude-code CHANGELOG #21274.
Claude Code v2.1.259 adds managedMcpServers so admins can push MCP servers to every developer machine. Validation allows only HTTPS/HTTP/SSE transports and rejects command/env stdio servers, keeping code-running local MCP on the machine while enabling safer org-wide managed configs.
Anthropic Academy is now official and free with no subscription required. It offers 13+ certificate courses spanning Claude 101 and Code in Action, Claude API (about 8 hours), Intro and Advanced MCP, Agent Skills, and Claude on AWS Bedrock and Google Vertex AI—aimed at developers learning Claude coding and agent toolchains end to end.
Discussion & Comments
0Sign in to join the discussion
Connect with AI developers to exchange benchmark insights.