Claude Report — 2026-06-24

🚀 Anthropic Official

Introducing Claude Tag (June 23)

Launches an always-on @Claude AI teammate for Slack, available in beta for Claude Enterprise and Team customers. Multiplayer by design — one shared Claude per channel; builds persistent organizational context over time by following channel activity; supports ambient mode (proactive monitoring and follow-ups on quiet threads); offers admin-scoped fine-grained tool and data access control. Runs on Opus 4.8 with introductory launch credits for eligible orgs.

Claude Code v2.1.187 (June 23)

Adds sandbox.credentials setting to block sandboxed commands from reading credential files and secret environment variables; adds org-configured model restrictions with a "restricted by your organization's settings" label in the model picker; adds mouse click support for select menus in fullscreen mode. Fixes: --resume failing with "No conversation found" for sessions with no model turns; --json-schema and workflow agent({schema}) structured output looping; remote MCP tool calls hanging up to 5 minutes (now abort with error); pasted Korean/CJK text rendering as mojibake; channel connections dropping when navigating to the agents view; and [VSCode] extension becoming unresponsive when resuming large sessions.

🔌 Claude Code Plugins

Plugin ranking cache unavailable this cycle — no feature-level plugin updates confirmed in the window.

Unchanged in window: tracking skipped — plugin ranking cache unavailable this cycle

🛠️ Skills

None of the top 5 updated in window (knowledge-work-plugins June 24 activity limited to automated dependency bumps; functional additions from June 22–23 were reported in the prior cycle).

Unchanged in window: anthropics/knowledge-work-plugins (dep bumps only on June 24), alirezarezvani/claude-skills, Piebald-AI/claude-code-system-prompts, glebis/claude-skills, ComposioHQ/awesome-claude-skills

🤖 Agents & Subagents

claude-agent-sdk-typescript v0.3.187 (June 23)

Adds sandbox.credentials to SDK settings types so TypeScript agent code can configure the new CLI credential-blocking capability introduced in Claude Code v2.1.187.

claude-agent-sdk-python v0.2.108 (June 23)

Bundles Claude CLI v2.1.187; sandbox.credentials support, org model restrictions, CJK mojibake fix, and all other v2.1.187 improvements land automatically on pip install --upgrade claude-agent-sdk.

Unchanged in window: nicobailon/pi-subagents, Chachamaru127/claude-code-harness

🔗 MCPs & Integrations

None of the top 5 updated in window.

Unchanged in window: github/github-mcp-server, modelcontextprotocol/python-sdk, modelcontextprotocol/typescript-sdk, awslabs/mcp, portainer/portainer-mcp

💡 Community — Workflows & Ideas

No relevant news today.

📰 Quick Mentions

Relevant links that don't warrant a section of their own:

• anthropics/claude-code-action v1.0.155 (June 23) — filters PR reviews and inline review comments by trigger time; fixes @ characters in git branch names; CI pipelines on @latest pick up both fixes automatically
• Claude Code v2.1.185 (June 21) — minor UX fix: stream-stall hint now reads "Waiting for API response, will retry in…" and triggers after 20 seconds instead of 10
• Anthropic updates privacy policy for biometric ID checks (June 22) — starting July 8, flagged Claude Free/Pro/Max users may be required to submit a government-issued ID, selfie, and facial geometry scan via third-party vendor Persona; Team/Enterprise/API users are exempt
• Claude 90-minute outage (June 23) — elevated error rates across Claude.ai, API, Claude Code, and Cowork for ~90 minutes from ~14:08 UTC; Anthropic's tenth infrastructure disruption in three weeks, with over 8,000 Downdetector reports at peak