MindPattern
← The Wire

Tools2026-06-29 · source-backed

Claude Code v2.1.194–195 adds trusted-device gating and a flag to kill mouse clicks.

Confidence
source-backed
Sources
1
Redaction
redacted

Story

Per the changelog, Anthropic shipped a Trusted Devices control letting Team/Enterprise admins require device verification before a member can view or steer local Claude Code sessions remotely. v2.1.195 adds CLAUDE_CODE_DISABLE_MOUSE_CLICKS, which kills fullscreen click/drag/hover while keeping wheel scroll, fixes hook matchers with hyphenated identifiers like code-reviewer and mcpbrave-search, and improves background-agent reliability plus Linux voice detection. The hyphenated-hook fix is small but real if you've ever had a hook silently not fire. The mouse-click flag is a quiet quality-of-life win for terminal setups where stray clicks hijack your session.

Related stories

Each link below shares sources, entities, or timing with this story.

  1. Shared entities / Same source domain / Shared topic / Earlier coverage

    Claude Code rate limits doubled across all plans.

    Both cover Anthropic, Claude Code, Enterprise, Team; reported by the same outlet (code.claude.com); overlapping topics (anthropic, claude, code).

  2. Shared entities / Shared topic / Earlier coverage

    Claude Code Artifacts turn an agent session into a live, shareable app.

    Both cover Anthropic, Claude Code, Enterprise, Team; overlapping topics (anthropic, claude, code, session); earlier Anthropic coverage from 2026-06-19.

  3. Anthropic added enterprise-managed MCP connectors with Okta.

    Both cover Anthropic, Claude Code, Enterprise, Team; overlapping topics (admin, anthropic, claude, control); earlier Anthropic coverage from 2026-06-19.

  4. Anthropic Rewrites the Economics of AI Agents. You Have 32 Days.

    Both cover Anthropic, Claude Code, Enterprise, Team; overlapping topics (anthropic, claude, code); earlier Anthropic coverage from 2026-05-13.

  5. Anthropic Doubles Claude Code Rate Limits and Signs the Biggest AI Compute Deal in History

    Both cover Anthropic, Claude Code, Enterprise, Team; overlapping topics (anthropic, claude, code); earlier Anthropic coverage from 2026-05-07.

  6. Anthropic Engineers Say Stop Building Agents, Build Skills Instead

    Both cover Anthropic, Claude Code, Enterprise, Team; overlapping topics (anthropic, claude, code); earlier Anthropic coverage from 2026-04-21.

  7. Shared entities / Shared topic / What happened next

    Anthropic launches Claude Science, admits it's the same model

    Both cover Anthropic, Enterprise, Linux, Team; overlapping topics (anthropic, claude); picks up the Anthropic thread on 2026-07-01.

  8. Shared entities / Same source / Shared topic / Earlier coverage

    Claude Code's June updates doubled rate limits and added nested skills.

    Both cover Anthropic, Claude Code; cite the same source (changelog); overlapping topics (anthropic, claude, code).

Source trail

changelog

Entities

AnthropicClaude CodeEnterpriseLinuxTeamTrusted Devices

Provenance

Canonical issue
Ramsay Research Agent — June 29, 2026
AI generated
no
Story unit
2026-06-29-claude-code-v2-1-194195-adds-trusted-device-gating-and-a-flag-to-kill-mouse-clicks
Labels
source-backed, canonical briefing excerpt