Claude Code introduces plugin eval command

// 1h agoPRODUCT UPDATE

Claude Code introduces plugin eval command

Anthropic's Claude Code version 2.1.269 introduces claude plugin eval, a native testing utility built directly into the CLI to automate plugin maintenance. Running the command within a plugin directory automatically suggests test cases and runs them to verify expected plugin behavior.

// ANALYSIS

Automated evaluation is rapidly becoming the most critical missing layer in the agentic developer stack. Model upgrades regularly shift tool-calling behavior, system prompt sensitivity, and edge-case reasoning, making plugin maintenance more demanding than initial development. Generating and running automated evaluations directly from the CLI significantly lowers the friction of maintaining plugin reliability. Integrating native evals into agent ecosystems mirrors traditional CI/CD workflows, nudging stochastic prompt engineering toward standard software engineering rigor.

// TAGS

claude-codeanthropicagentdevtoolevaluationplugins

DISCOVERED

1h ago

2026-09-13

PUBLISHED

1h ago

2026-09-13

RELEVANCE

8/ 10

AUTHOR

stretchcloud

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

OPEN SOURCE1h ago

Show-Harness lets foundation VLMs control physical robots

Show-Harness is an open-source framework developed by Show Lab at the National University of Singapore that connects vision-language models directly to robotic control systems. By translating discrete semantic action units into deterministic metric motions across diverse robot platforms, it enables zero-shot manipulation with frontier VLMs and high-frequency execution on lightweight models with minimal fine-tuning.

RESEARCH1h ago

Fire3D reconstructs simulation-ready 3D scenes from images

Fire3D is an open-source feed-forward framework that reconstructs complete, simulation-ready 3D indoor scenes from an unsegmented RGB image or casual video in under 60 seconds without per-scene test-time optimization. Instead of outputting view-dependent rendering fields, Fire3D decomposes scenes into discrete objects and background structures, generating 6-DoF poses, watertight geometry, and PBR textures tailored for robotics simulations and game engines.

RESEARCH1h ago

UMR unifies humanoid motion retargeting with point clouds

Researchers from HKUST(GZ), Noitom Robotics, and Hanyang University introduced Unified Motion Retargeting (UMR), a framework that translates diverse human motion capture data into robot-ready trajectories across heterogeneous humanoid embodiments. By establishing learned dense point cloud correspondences on robot body meshes, UMR decouples retargeting from skeletal semantics while preserving surface alignment and fine-grained contact dynamics.