Curated tools for Claude Code, without the noise.

Claude Opus 4.8 · Claude Opus 4.8 builds on Claude Opus 4.7 with improvements across benchmarks and is a more effective collaborator, available today for the same price. It targets long-horizon agentic coding with better long-context handling and compaction recovery, more reliable effort calibration, and better tool triggering. The model ID is claude-opus-4-8; it supports the 1M token context window by default on the Claude API, Amazon Bedrock, and Vertex AI, with 128k max output tokens.

Dynamic workflows in Claude Code · Claude breaks a problem into subtasks and fans them out across tens to hundreds of subagents running in parallel, dynamically writing orchestration scripts that run in a single session and checking its work before anything reaches you. It targets broad work like codebase-wide bug hunts and security audits and large migrations spanning thousands of files, verifying each result before folding it into the final answer. Available as a research preview on Max, Team, and Enterprise plans.

Claude Managed Agents — Self-hosted sandboxes and MCP tunnels · Claude Managed Agents now supports self-hosted sandboxes (public beta) and MCP tunnels (research preview). The agent orchestration loop stays on Anthropic infrastructure while tool execution runs in customer infrastructure or with managed sandbox providers — Cloudflare, Daytona, Modal, Vercel — and agents reach private-network MCP servers through a lightweight gateway with a single outbound connection, no inbound firewall rules required.

Agent view in Claude Code · Agent view is a centralized interface inside the Claude Code CLI for managing multiple concurrent agent sessions. Now in Research Preview, it lets developers see which agents need input, are actively working, or have completed tasks — and scale up background work via peek, `/bg`, and `claude --bg`.

Claude Platform on AWS is now generally available · The Claude Platform on AWS — Anthropic-operated, accessed via AWS IAM with CloudTrail audit logging and a single AWS invoice — is generally available. AWS customers get day-one access to all native Claude API features, including Claude Managed Agents (beta), Advisor strategy (beta), Files API (beta), Skills (beta), and the MCP connector (beta), with Claude Opus 4.7, Sonnet 4.6, and Haiku 4.5 available at launch.

Claude Code 2.1.169 · The new `--safe-mode` flag (and `CLAUDE_CODE_SAFE_MODE` env) starts Claude Code with all customizations (CLAUDE.md, plugins, skills, hooks, MCP servers) disabled for troubleshooting, and `/cd` moves a session to a new working directory without breaking the prompt cache. `disableBundledSkills` (and `CLAUDE_CODE_DISABLE_BUNDLED_SKILLS`) hides bundled skills, workflows, and built-in slash commands from the model. Fixes for enterprise managed MCP policies (`allowedMcpServers`/`deniedMcpServers`) not being enforced on reconnect or IDE-typed configs, Up/Down arrows jumping past wrapped rows of a long input, a 30-50ms per-turn UI stall on macOS with claude.ai credentials, and `claude -p` being slow on Windows (regression in 2.1.161) also land.

Claude Code 2.1.166 · The new `fallbackModel` setting takes up to three fallback models tried in order when the primary is overloaded or unavailable, and `--fallback-model` now also applies to interactive sessions. Deny rules accept glob patterns in the tool-name position (`"*"` denies all tools), and messages relayed via `SendMessage` from other Claude sessions no longer carry user authority. `MAX_THINKING_TOKENS=0`, `--thinking disabled`, and the per-model thinking toggle now disable thinking on default-thinking models via the Claude API, and Claude Code retries a turn once on the fallback model when the API returns an unexpected non-retryable error. Plus fixes for remote sessions stuck during worker registration, JetBrains 2026.1+ terminal flicker, Shift+non-ASCII characters dropped under the Kitty keyboard protocol, and managed settings whose single invalid entry silently disabled enforcement of the rest.

Claude Code 2.1.163 · Claude Code 2.1.163 lands enterprise version pinning, plugin listing, and several agent-loop ergonomics. `requiredMinimumVersion` and `requiredMaximumVersion` managed settings refuse to start outside an approved range, `/plugin list` lists installed plugins with `--enabled`/`--disabled` filters, and Stop and SubagentStop hooks can return `hookSpecificOutput.additionalContext` to keep the turn going. stdio MCP servers now receive `CLAUDE_CODE_SESSION_ID` on `--resume`. The release also fixes `claude -p` hanging on backgrounded commands, a `$TMPDIR` override regression from 2.1.154, org-managed permission rules missing parts of startup, and a broad sweep of background-session, Windows, and terminal-UI bugs.

Claude Code 2.1.162 · `claude agents --json` now includes `waitingFor` showing what a waiting session is blocked on, and `--tools` finally provides the dedicated Grep/Glob tools on native builds when you list them. Slash command autocomplete clicks now fill the prompt instead of running immediately, and Remote Control moves from a startup message to a persistent footer pill. Plus a round of fixes for silent startup hangs on read-only config dirs, WebFetch permission rules being skipped for preapproved domains, and Windows permission rules never matching backslash paths.

Claude Code 2.1.161 · `OTEL_RESOURCE_ATTRIBUTES` values are now included as labels on metric datapoints so usage can be sliced by custom dimensions like team or repo, and a failed Bash in a parallel tool batch no longer cancels its siblings. Fullscreen Linux clipboard now uses `wl-copy`/`xclip`/`xsel` and copies to both the clipboard and PRIMARY selection. Plus fixes for `claude mcp` printing secrets to the terminal and the `forceLoginOrgUUID`/`forceLoginMethod` managed-settings regression (2.1.146) that blocked Bedrock, Vertex, Foundry, and Mantle sessions.