Kick off plan mode in the cloud from your terminal, then review the result in your browser. Claude drafts the plan in a Claude Code on the web session while your terminal stays free; when it's ready you comment on individual sections, ask for revisions, and choose to execute remotely or send it back to your CLI. As of v2.1.101 the first run auto-creates a default cloud environment, so there's no web setup step before you can try it.

Run the command, or just include the keyword in any prompt:

> /ultraplan migrate the auth service from sessions to JWTs

Ultraplan guide

A new built-in tool that spawns a background watcher and streams its events into the conversation: each event lands as a new transcript message that Claude reacts to immediately. Tail a training run, babysit a PR's CI, or auto-fix a dev server crash the moment it happens, all without a Bash sleep loop holding the turn open.

Ask Claude to watch something while you keep working:

> Tail server.log in the background and tell me the moment a 5xx shows up

This pairs with /loop, which now self-paces: omit the interval and Claude schedules the next tick based on the task, or reaches for the Monitor tool to skip polling altogether.

> /loop check CI on my PR

Monitor tool reference

PR auto-fix landed on the web in Week 13. Now you can turn it on without leaving your terminal: /autofix-pr infers the open PR for your current branch and enables auto-fix for it on Claude Code on the web in one step. Push your branch, run the command, walk away; Claude watches CI and review comments and pushes fixes until it's green.

Run it from the PR's branch:

> /autofix-pr

Auto-fix pull requests

Generates a teammate ramp-up guide from your local Claude Code usage. Run it in a project you know well and hand the output to a new teammate so they can replay your setup instead of starting from defaults.

Run it from a project you've spent real time in:

> /team-onboarding

Commands reference

Other wins

Last week computer use landed in. This week it's in the CLI: Claude can open native apps, click through UI, test its own changes, and fix what breaks, all from your terminal. Web apps already had verification loops; native iOS, macOS, and other GUI-only apps didn't. Now they do. Best for closing the loop on apps and tools where there's no API to call. Still early; expect rough edges.

Run /mcp, find computer-use, and toggle it on. Then ask Claude to verify a change end to end:

> Open the iOS simulator, tap through onboarding, and screenshot each step

Computer use guide

Interactive lessons that teach Claude Code features through animated demos, right inside your terminal. Claude Code releases frequently, and features that would have changed how you work last month can slip by. Run /powerup once and you'll know what's there.

Run it:

> /powerup

Commands reference

Opt into a new alt-screen renderer with virtualized scrollback. The prompt input stays pinned to the bottom, mouse selection works across long conversations, and the flicker on redraw is gone. Unset CLAUDE\_CODE\_NO\_FLICKER to roll back.

Set the env var and restart Claude Code:

export CLAUDE_CODE_NO_FLICKER=1
claude

Fullscreen rendering

MCP server authors can now raise the truncation cap on a specific tool by setting anthropic/maxResultSizeChars in the tool's tools/list entry, up to a hard ceiling of 500K characters. The cap used to be global, so tools that occasionally returned inherently large payloads like database schemas or full file trees hit the default limit and got persisted to disk with a file reference. Per-tool overrides keep those results inline when the tool really needs them.

Annotate the tool in your server's tools/list response:

{
  "name": "get_schema",
  "description": "Returns the full database schema",
  "_meta": {
    "anthropic/maxResultSizeChars": 500000
  }
}

MCP reference

Place an executable in a bin/ directory at your plugin root and Claude Code adds that directory to the Bash tool's PATH while the plugin is enabled. Claude can then invoke the binary as a bare command from any Bash tool call, with no absolute path or wrapper script needed. Handy for packaging CLI helpers next to the commands, agents, and hooks that call them.

Add a bin/ directory at the plugin root:

my-plugin/
├── .claude-plugin/
│   └── plugin.json
└── bin/
    └── my-tool

Plugins reference

Other wins

Auto mode hands your permission prompts to a classifier. Safe edits and commands run without interrupting you; anything destructive or suspicious gets blocked and surfaced. It's the middle ground between approving every file write and running with --dangerously-skip-permissions.

Cycle to auto with Shift+Tab, or set it as your default:

{
  "permissions": {
    "defaultMode": "auto"
  }
}

Permission modes guide

Flip a switch when you open a PR and walk away. Claude watches CI, fixes the failures, handles the nits, and pushes until it's green. No more babysitting a PR through six rounds of lint errors.

After creating a PR on Claude Code web, toggle Auto fix in the CI panel.

Auto-fix pull requests

Press / in transcript mode to search your conversation. n and N step through matches. Finally a way to find that one Bash command Claude ran 400 messages ago.

Open transcript mode and search:

Ctrl+O    # open transcript
/migrate  # search for "migrate"
n         # next match
N         # previous match

Fullscreen guide

Windows gets a native PowerShell tool alongside Bash. Claude can run cmdlets, pipe objects, and work with Windows-native paths without translating everything through Git Bash.

Opt in from settings:

{
  "env": {
    "CLAUDE_CODE_USE_POWERSHELL_TOOL": "1"
  }
}

PowerShell tool docs

Hooks can now declare an if field using permission rule syntax. Your pre-commit check only spawns for Bash(git commit \*) instead of every bash call, cutting the process overhead on busy sessions.

Scope a hook to git commits only:

{
  "hooks": {
    "PreToolUse": [{
      "hooks": [{
        "if": "Bash(git commit *)",
        "type": "command",
        "command": ".claude/hooks/lint-staged.sh"
      }]
    }]
  }
}

Hooks reference

Other wins