Claude agent worktrees

Skill Xopoko/plug-n-skills/plugins/claude-code/skills/claude-agent-worktrees

Ready-to-install skills and plugins for Codex, Claude Code, and AI coding agents: practical workflows for app delivery, architecture, research, design, and agent tooling.

Install

npx -y skills add Xopoko/plug-n-skills --skill claude-agent-worktrees

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when coordinating Claude Code background agents, `claude agents --json`, dispatched-session defaults, git worktrees, tmux/iTerm panes, resume/continue/from-pr/fork-session, session names and IDs, remote control, prompt suggestions, or cloud ultrareview runs.

SKILL.md

3.6 KB, as published. Nobody here has run it

Claude Agents And Worktrees

Bundled commands use $PLUGIN_ROOT ($env:PLUGIN_ROOT in PowerShell; same path suffix) for the plugin root. Set it once: use the host's plugin-root variable when defined (Claude Code: PLUGIN_ROOT="$CLAUDE_PLUGIN_ROOT"), otherwise the absolute path of this plugin's root directory.

Use this skill for Claude Code session orchestration: background agents, worktrees, tmux/iTerm panes, resumes, PR-linked sessions, forked sessions, session names and IDs, remote control, prompt suggestions, and cloud ultrareview.

Inspect First

Check command surface and current background sessions:

python3 "$PLUGIN_ROOT/scripts/claude_code_inspector.py" --commands agents ultrareview --json
claude agents --json

Use claude agents --json --all only when completed sessions are relevant and the extra transcript/session metadata is needed.

Background Agents

Use claude agents for active background session state and dispatch defaults:

claude agents --json
claude agents --cwd /path/to/project --json
claude agents --model sonnet --permission-mode plan --add-dir /path/to/extra

Do not start or leave long-lived background sessions without a reason and a cleanup plan. Use explicit model, permission mode, settings, plugin-dir, and MCP config when reproducibility matters.

Sessions

Use these root flags for session continuity:

claude --continue
claude --resume <session-id-or-search>
claude --from-pr <pr-number-or-url>
claude --fork-session --resume <session-id>
claude --session-id <uuid>
claude --name "display-name"

Prefer exact session IDs or PR URLs when the user wants a specific conversation. Use search/pickers only for interactive use.

Worktrees And Panes

Use worktrees when the task should be isolated from the current working tree:

claude --worktree
claude --worktree feature-name --tmux
claude --worktree feature-name --tmux=classic

Before creating worktrees, inspect git status and branch state. Do not create extra worktrees for tiny one-off commands unless isolation is the point.

Remote Control And Integrations

Remote control, IDE, and Chrome integration are interactive surfaces:

claude --remote-control
claude --remote-control "session-name"
claude --ide
claude --chrome
claude --no-chrome

Use them only when the user asks for those integrations. Report how to stop or exit any interactive session started.

Ultrareview

claude ultrareview is cloud-hosted and may consume time or quota. Run it only when requested:

claude ultrareview
claude ultrareview main
claude ultrareview <pr-number-or-url> --json --timeout 30

Prefer local review or --print analysis for lightweight checks.

Safety Boundaries

Do not combine background dispatch with dangerous skip-permissions unless the user selected an external sandbox.
Do not create worktrees, tmux sessions, or remote-control sessions without clear user intent.
Do not purge or abandon background work without reporting the session state.
Do not expose session IDs, PR URLs, or transcript snippets beyond what the user needs.

Completion Standard

Report the current session/agent/worktree state inspected, exact command used, permission/tool settings, any created session/worktree/pane name, and cleanup or resume instructions when a process remains active.