Keep a Mac awake for a chosen duration or while a specified process runs. The skill uses built-in macOS tools to manage one session, verify that sleep prevention is active, and control whether the display stays on.
Keep a Mac awake for a set duration or while a process runs. Use only when the user explicitly invokes /anti-sleep.
Review the instructions the agent will receive before you install.
Use the bundled launcher from this skill directory. It creates a one-shot user LaunchAgent using only built-in macOS tools.
Never launch caffeinate with raw &, nohup, disown, or launchctl submit. Temporary execution shells can kill their descendants, and launchctl submit can restart a timed job.
Resolve scripts/anti-sleep.sh relative to this SKILL.md; never assume the user's current directory. Run:
scripts/anti-sleep.sh status
status reports an active session and the user requested a new duration, automatically stop the old session. Never ask for confirmation.scripts/anti-sleep.sh stop
scripts/anti-sleep.sh start 10800 # 3 hours
For a specific process, use start-pid. Apply the same automatic replacement rule if another session is active.
scripts/anti-sleep.sh start-pid <PID>
scripts/anti-sleep.sh verify
Only report success when verification returns STATUS=running and ASSERTIONS=active. Confirm the PID, flags, and wall-clock expiry. If verification fails, run stop and do not claim the Mac is protected.
The default is -d -i: keep the display on and prevent idle system sleep. Pass explicit flags after the duration or PID when needed:
| Flags | Effect |
|---|---|
-i | Prevent idle system sleep; display may dim |
-d | Prevent display sleep |
-d -i -s | Also prevent system sleep while on AC power |
None of these stop sleep when the lid closes. For agent runs that must survive a closed lid, see Keep Claude Code running when your laptop is closed.
Example:
scripts/anti-sleep.sh start 10800 -i
scripts/anti-sleep.sh status
scripts/anti-sleep.sh stop
The launcher tracks one exact LaunchAgent label, PID, start time, and expiry under ~/Library/Caches. It never uses broad pkill.
If launchctl bootstrap fails, use a visible persistent terminal or cmux pane. Read the cmux skill before interacting with cmux. If no persistent surface is available, tell the user instead of starting an unreliable background job.
caffeinate cannot keep the keyboard backlight on. That setting is manual: System Settings → Keyboard → “Turn keyboard backlight off after inactivity” → Never.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Work through sixteen open questions in four rounds to clarify major product decisions, risky changes, or large refactors. The agent adapts later questions to earlier answers, then turns your decisions into a step-by-step implementation plan.
Document approved decisions as concise ADRs, or architecture decision records. It preserves the user's meaning and conditions, removes conversational filler, follows the project's numbering, and presents the saved record for review.
Turn a feature or refactoring idea into a concise implementation prompt for another agent. It asks focused questions one at a time, records decisions, and includes development steps, validation, and working rules.
Inspect and manage BB threads, environments, projects, and plugins through its command line interface. The skill guides agents to identify the correct targets, apply changes, and verify the resulting state.
Create, install, and debug TypeScript plugins that extend bb with custom pages, sidebar panels, CLI commands, agent tools, themes, and other features. The skill also guides development reloads, log checks, and verification of installed plugins.
Identify one to three important decisions before starting a build. Based on the user's idea, this skill presents concise options and an initial recommendation for each, then waits for answers before work proceeds.