### Get full orchestration skill guide Source: https://www.onorca.dev/docs/cli/orchestration Run this command after installing the app to retrieve the full, up-to-date guide for the orchestration skill, since command flags evolve with the app. ```bash orca skills get orchestration --full ``` -------------------------------- ### Create run, task, and start supervised worker Source: https://www.onorca.dev/docs/cli/orchestration Preferred supervised loop: create a run, create a task, then start a worker. Use --worktree current to reuse the current worktree, or --worktree new-child with --name and --setup run for a new child worktree. --model accepts opaque provider model IDs for Claude, Codex, Muse, Cursor, and Antigravity; --effort requires --model and only applies when the agent/model supports it. Neither flag can combine with --terminal. Overrides apply only to that launch and show under launch.requested / launch.effective in the start receipt. Federated starts need a worker host that advertises launch-preference support. Orca prepares trust for a local Antigravity child worktree before starting its worker; Antigravity supervision over SSH is not supported by this trust setup. ```bash orca orchestration run-create --objective "Split checkout QA and summarize blockers" --json orca orchestration task-create --spec "Audit billing settings for mobile layout" --task-title "Billing audit" --json orca orchestration worker-start --task --worktree current --agent codex --json # or new worktree: orca orchestration worker-start --task --worktree new-child --name billing-audit --agent codex --setup run --json # optional per-worker model / effort (Claude, Codex, Muse, Cursor, Antigravity; not with --terminal): orca orchestration worker-start --task --worktree current --agent claude --model --effort high --json # Run Antigravity as a supervised worker in a local child worktree: orca orchestration worker-start --task --worktree new-child --name research --agent antigravity --setup run --json ``` -------------------------------- ### Start headless Orca server with orca serve Source: https://www.onorca.dev/docs/remote-servers Commands to start the Orca runtime headlessly on a server. The first shows the placeholder form; the second is a concrete example. Add --port 6768 for a fixed port, and --mobile-pairing to get a mobile-scoped QR code and link. The command runs in the foreground until Ctrl-C and prints the bound endpoint and pairing URL. ```bash orca serve --pairing-address ``` ```bash orca serve --pairing-address 100.64.1.20 ``` ```bash orca serve --port 6768 --pairing-address 100.64.1.20 ``` ```bash orca serve --pairing-address 100.64.1.20 --mobile-pairing ``` -------------------------------- ### List, get, install, and update Orca skills Source: https://www.onorca.dev/docs/cli/reference Manage bundled guides and hybrid skill packages without the desktop Settings UI. `install` and `update` shell out to the same `npx skills` commands Settings uses and do not contact the Orca runtime. ```bash orca skills list orca skills get orca-cli orca skills get orchestration --full orca skills install --skill orca-cli --skill orchestration orca skills install --all --dry-run orca skills update --all ``` -------------------------------- ### List and get skills with orca skills Source: https://www.onorca.dev/docs/cli/skills Commands to list available skills and retrieve guides. Use `--json` for deterministic output in automation. `skills show` is an alias for `skills get`. ```bash orca skills list orca skills get orca-cli orca skills get orchestration --full orca skills get orca-linear --json ``` -------------------------------- ### Install computer-use skill Source: https://www.onorca.dev/docs/cli/skills Installs the computer-use skill globally. Use for desktop apps via accessibility trees and safe UI actions. ```bash npx skills add https://github.com/stablyai/orca --skill computer-use --global ``` -------------------------------- ### Install computer-use skill Source: https://www.onorca.dev/docs/cli/computer-use Install the shipped computer-use skill into the agent's skill directory. See Skills registry & MCP for how skills are picked up. ```bash npx skills add https://github.com/stablyai/orca --skill computer-use ``` -------------------------------- ### Create automation with project host setup Source: https://www.onorca.dev/docs/cli/automations Creates a disabled automation targeting a specific project host setup. Use --project and --host to specify the destination, or --project-host-setup when you already have a setup id. Optional --source-context '' pins task/provider data to a host/account; pass null on edit to clear. ```bash orca automations create \ --name "Remote triage" \ --trigger daily \ --time 09:00 \ --prompt "Triage open issues" \ --provider claude \ --project \ --host \ --disabled \ --json ``` -------------------------------- ### Install orca-per-workspace-env skill Source: https://www.onorca.dev/docs/cli/skills Installs the orca-per-workspace-env skill globally. Use for per-workspace environment recipes (orca.yaml). ```bash npx skills add https://github.com/stablyai/orca --skill orca-per-workspace-env --global ``` -------------------------------- ### Worktree create with agent startup flags Source: https://www.onorca.dev/docs/cli/reference Launch agents in worktrees with --agent, send initial work with --prompt, and control repo setup hooks with --setup run|skip|inherit. inherit follows the repo policy. ```bash orca worktree create --name review-api --agent claude --setup run --json orca worktree create --name quick-check --agent codex --prompt "Summarize the diff" --setup skip --json orca worktree create --name hidden-setup --setup inherit --json ``` -------------------------------- ### Install orca-linear skill Source: https://www.onorca.dev/docs/cli/skills Installs the orca-linear skill globally. Use for Linear ticket read/write through 'orca linear'. ```bash npx skills add https://github.com/stablyai/orca --skill orca-linear --global ``` -------------------------------- ### Install orca-emulator skill Source: https://www.onorca.dev/docs/cli/skills Installs the orca-emulator skill globally. Use for iOS Simulator control. ```bash npx skills add https://github.com/stablyai/orca --skill orca-emulator --global ``` -------------------------------- ### Install orca-emulator-android skill Source: https://www.onorca.dev/docs/cli/skills Installs the orca-emulator-android skill globally. Use for Android emulator/device via adb. ```bash npx skills add https://github.com/stablyai/orca --skill orca-emulator-android --global ``` -------------------------------- ### Headless skills install and update commands Source: https://www.onorca.dev/docs/cli/skills Local CLI wrappers for headless hosts (SSH, containers, CI, `orca serve`) that resolve the same `npx` commands with non-interactive flags. Default scope is global; use `--local` for current project. `install` targets detected agents; `--agent` is required if none detected. `update` only refreshes installed skills. `--dry-run` prints the resolved command; `--json` is only valid with listing or `--dry-run`. ```bash orca skills install # list installable names orca skills install --skill orca-cli --skill orchestration orca skills install --skill orca-cli --agent claude-code,codex orca skills install --all --dry-run orca skills update --all orca skills update --skill orca-cli --dry-run ``` -------------------------------- ### Install orca-cli skill Source: https://www.onorca.dev/docs/cli/skills Installs the orca-cli skill globally from the Orca repo. Use for worktrees, terminals, files, automations, and embedded browser. ```bash npx skills add https://github.com/stablyai/orca --skill orca-cli --global ``` -------------------------------- ### Start Orca and verify status Source: https://www.onorca.dev/docs/cli/reference Starts Orca if it is not already running, then verifies the runtime is reachable. Use --json when another tool will parse the result. ```shell orca open --json orca status --json ``` -------------------------------- ### Install Orca CLI skill Source: https://www.onorca.dev/docs/cli/overview Install the Orca CLI skill for agents. The first command uses npx to add the skill from the GitHub repository; the second is the headless alternative when no Settings UI is available. ```bash npx skills add https://github.com/stablyai/orca --skill orca-cli # headless / no Settings UI: orca skills install --skill orca-cli ``` -------------------------------- ### Start federated worker and send follow-up Source: https://www.onorca.dev/docs/cli/orchestration Starts a federated worker on Windows with a new top-level worktree, then sends a follow-up message to the dispatch ID. Later commands route by Dispatch ID; do not repeat `--on`. ```shell orca orchestration worker-start \ --task \ --on windows \ --worktree new-top-level \ --repo \ --name remote-worker \ --agent codex \ --setup run \ --json orca orchestration send --to dispatch: --subject "Follow-up" --body "…" --json ``` -------------------------------- ### orca computer commands for desktop apps Source: https://www.onorca.dev/docs/cli/reference Commands for native desktop apps outside the built-in browser. Use `orca computer` for permissions, listing apps, getting app state, clicking elements, and pasting text. See Computer use for the full workflow and permission setup. ```bash orca computer permissions --json orca computer list-apps --json orca computer get-app-state --app com.apple.Safari --json orca computer click --app com.apple.Safari --element-index 12 --json orca computer paste-text --app com.apple.Safari --text "hello" --json ``` -------------------------------- ### Install orchestration skill Source: https://www.onorca.dev/docs/cli/skills Installs the orchestration skill globally. Use for multi-agent runs, tasks, supervised workers, messages, and gates. ```bash npx skills add https://github.com/stablyai/orca --skill orchestration --global ``` -------------------------------- ### Start Orca server with orca serve Source: https://www.onorca.dev/docs/ways-to-run Run Orca as a headless server on a Linux machine or service-managed VM. Use a reachable Tailscale IP or hostname as the pairing address so clients can connect. ```bash orca serve --pairing-address ``` -------------------------------- ### Request per-workspace environment setup Source: https://www.onorca.dev/docs/ways-to-run Ask the agent to set up a per-workspace environment using the orca-per-workspace-env skill. The skill walks through prerequisites, base snapshot, agent auth, orca.yaml recipe, and doctor validation. ```text Use the orca-per-workspace-env skill to set up a per-workspace environment for this repo. ```