AugmentClaude

AO CLI

Spawn workers, manage sessions, and control the AO daemon from your terminal.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/using-ao-agentwrapper/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Catalog of the AO (Agent Orchestrator) `ao` CLI: spawning workers, managing sessions and projects, sending messages, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.

What this skill does

AO CLI Catalog

ao is a thin CLI over the local AO daemon. Every command is ao <command> --help for the authoritative flag list.

CommandWhat it doesWhen to useDetails
spawnSpawn a worker agent in a fresh git worktreeStarting a new task or issuecommands/spawn.md
sessionManage agent sessions (list, kill, rename, restore, etc.)Inspecting or controlling running/terminated sessionscommands/session.md
projectRegister, inspect, configure, or remove projectsSetting up or managing repos AO knows aboutcommands/project.md
orchestratorList orchestrator sessionsViewing which sessions are orchestratorscommands/orchestrator.md
reviewSubmit a reviewer result for a worker's PRCompleting a code review loopcommands/review.md
sendSend a message to a running agent sessionCorrecting or directing a live agentcommands/send.md
previewOpen a URL in the desktop browser panelDemoing a local server or file from inside a sessioncommands/preview.md
startFetch (if needed) and open the AO desktop appLaunching the appcommands/start.md
stopStop the AO daemonShutting down AOcommands/stop.md
statusShow daemon statusVerifying the daemon is up and healthycommands/status.md
doctorRun local health checksDiagnosing AO setup problemscommands/doctor.md
importImport projects from a legacy AO installMigrating from the old flat-file storecommands/import.md
versionPrint version informationChecking installed version-
completionGenerate shell completion scriptsSetting up tab completion-

Conventions

  • Most read commands accept --json for machine-readable output.
  • -p / --project scopes session subcommand lookups to one project.
  • Session and project ids are shown by ao session ls and ao project ls.
  • --agent is an alias for --harness on ao spawn.
  • Every command accepts -h / --help for the full flag list.

See references.md for natural-language-to-command mappings.

Related skills