Fetching from the wire…
Tools2026-07-14 · source-backed
It patches leaks that only bite over time: MCP stdio server stderr accumulating unbounded, LSP documents staying open indefinitely, and pasted images retained in the agent view (Releasebot). On top of that, background agents now commit, push, and open a draft PR on completion instead of stopping to ask, the Explore agent inherits your session model capped at opus instead of running on haiku, and there's a new /doctor check that proposes trimming CLAUDE.md content Claude can already derive from the codebase. There's also an opt-in plain-text screen-reader mode via claude --ax-screen-reader. If you run 24/7 agents or headless -p loops, the memory fixes alone are the reason to update today rather than waiting for a feature you want.
Each link below shares sources, entities, or timing with this story.
The v2.1.205 release turned /doctor into a full setup audit that flags unused skills, MCP, and plugins against their context cost, deduplicates local vs checked-in CLAUDE.md, and flags slow hooks (Releasebot). A typical 5-server, 58-tool MCP setup burns ~55k tokens before your...
Two researchers in my set surfaced this independently, which is usually a sign it matters. Claude Code 2.1.166, first seen June 6, introduces a fallback-models setting: configure up to three models tried in order when the primary is overloaded or unavailable. It also adds glob...
Cursor 3 launched on April 2. Not an update. A full rebuild. The editor is now secondary to what they're calling an agent orchestration workspace. You can run unlimited parallel agents, locally or in the cloud, launch them from your phone or Slack or Linear, and manage them in...
Lasso Security published research demonstrating that Claude Code's --dangerously-skip-permissions flag enables indirect prompt injection via poisoned READMEs, documentation files, and MCP responses. Then they did something unusual: they released the defense alongside the attac...
It now dedupes local CLAUDE.md files against checked-in ones, proposes trimming content it can derive from the codebase, ranks unused skills, MCP servers, and plugins by context cost, and flags slow hooks. Background subagents run by default and, when launched from claude agen...
This one rearranged my week. An essay published August 4 walks through Databricks' independent benchmark of coding harnesses against its own multi-million-line codebase. Pi, a harness with four built-in tools and a system prompt under 1,000 tokens, paired with Opus 4.8 at xhig...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.