minssam.
80 POSTS

Anthropic.

Posts tagged 'Anthropic'.

NOTE / 031

claude plugin eval: Prove Your Plugin's Value With Numbers

Anthropic added the claude plugin eval command to Claude Code v2.1.269 (September 11, 2026). Every test case runs twice β€” once with the plugin loaded (with-arm) and once without (without-arm) β€” and the difference, Ξ”, is the plugin's measured contribution. Six grader types, JSON + HTML reports, and CI threshold flags complete a plugin quality-assurance pipeline.

NOTE / 033

Claude Fable 5.1: 75% Off Cache Reads, Change Reasoning Budget Mid-Conversation

Anthropic released Claude Fable 5.1 on September 1, 2026. At the same price as Fable 5 ($10/$50), cache read costs dropped 75% β€” from $1.00 to $0.25 per million tokens. Per-message effort control, now in beta, lets you change the reasoning budget mid-conversation without invalidating the prompt cache. 1M token context and always-on adaptive thinking are standard.

ClaudeFable51READ MORE β†—
NOTE / 034

Claude Code Projects Beta: An AI Coordinator Directs Parallel Sessions β€” Coding Continues Even After You Close Your Laptop

Anthropic completely redesigned Claude Code Projects and released it in beta on September 17, 2026. When a developer describes a goal, a coordinator session distributes work into threads, each running in parallel on its own branch in a cloud session. Shared memory and a project library maintain context across threads, and sessions keep running even after you close your laptop.

MINSSAM.COM