orca-loop
/orca-loop
Use `orca loop ...` to run an agent harness repeatedly in a worktree until a check command or evaluator condition says the work is done: create until-done, interval, or queue loops; list and inspect them; pause, resume (optionally granting more iterations), steer, edit, and stop. Use when the user says "orca loop", "run the agent in a loop", "keep going until the tests pass", "babysit this PR every N minutes", or asks to queue several prompts for an agent in order.
Assessment and security
- Files in this package
- 1
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 22.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
Use `orca loop ...` to run an agent harness repeatedly in a worktree until a check command or evaluator condition says the work is done: create until-done, interval, or queue loops; list and inspect them; pause, resume (optionally granting more iterations), steer, edit, and stop. Use when the user says "orca loop", "run the agent in a loop", "keep going until the tests pass", "babysit this PR every N minutes", or asks to queue several prompts for an agent in order.
Triggers from the description
Original author description
Use `orca loop ...` to run an agent harness repeatedly in a worktree until a check command or evaluator condition says the work is done: create until-done, interval, or queue loops; list and inspect them; pause, resume (optionally granting more iterations), steer, edit, and stop. Use when the user says "orca loop", "run the agent in a loop", "keep going until the tests pass", "babysit this PR every N minutes", or asks to queue several prompts for an agent in order.
How it works
- Resolve the CLI for this session
- Load the version-matched guide before running Orca commands
SKILL.md preview
--- name: orca-loop description: >- Use `orca loop ...` to run an agent harness repeatedly in a worktree until a check command or evaluator condition says the work is done: create until-done, interval, or queue loops; list and inspect them; pause, resume (optionally granting more iterations), steer, edit, and stop. Use when the user says "orca loop", "run the agent in a loop", "keep going until the tests pass", "babysit this PR every N minutes", or asks to queue several prompts for an agent in order. --- # Orca Loop This discovery stub loads the version-matched guide from the Orca executable used for this session. Use Orca's `loop` CLI to run an agent repeatedly in a worktree until a check or evaluator says it is done: create until-done, interval, or queue loops, list and inspect them, pause, resume with extra iterations, steer the next iteration, edit settings, and stop. Loops run inside the Orca app, so they outlive the command and the terminal tab. Start by reading the full guide before acting. ## Resolve the CLI for this session Choose the executable once and reuse it for every later command: - If the `ORCA_CLI_COMMAND` environment variable is set, use its value. Orca exports this for managed WSL sessions. - Otherwise, in a dev checkout whose session exposes `ORCA_DEV_REPO_ROOT`, use `orca-dev`. - Otherwise, on Linux outside an Orca-managed terminal, use `orca-ide`. Never run bare `orca` there — outside Orca's terminals it normally resolves to the GNOME Orca screen reader (`/usr/bin/orca`) and starts speech on the user's machine. - Otherwise, use `orca`. Below, `ORCA` is a placeholder for the executable you resolved. Substitute it before running anything; do not create a shell variable or run `ORCA` literally. This works the same way in POSIX shells, PowerShell, and cmd.exe. If the selected executable cannot run, report its exact error and stop. Do not fall through to another executable, which could silently target a different Orca build. ## Load the version-matched guide before running Orca commands ```text ORCA skills get orca-loop ``` Prefer `--json`. Use the selected executable's `--help` for commands or flags the guide does not cover. If a command reports that Orca is not running, start it with `ORCA open --json` and retry. If it fails with `runtime_access_denied`, your sandbox blocked the connection: re-run it with escalated permissions, and do not run `ORCA open` or restart Orca. If `skills get` is unknown, explain that updating Orca restores the guide; use `--help` for read-only discovery and do not guess unsupported commands.
Versions
The database has no other skills named orca-loop.
Database snapshot: 13.11.2026 · package version 30137801b33b (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 100orca-cli-local
Applies local lessons to every use of the Orca CLI (orca-ide, orca-dev). Use alongside the upstream orca-cli skill whenever the Orca CLI is needed, including before creating a branch worktree or asking the user for feedback on a change before committing while running inside Orca. - 100orca-setup
Configures a repository for Orca so every new worktree is ready to work: copies the gitignored env files from the main checkout and runs pnpm install. Use when the user asks to set up Orca, add or fix orca.yaml, configure worktree setup/archive hooks, or when a new Orca worktree… - 100orca
Orca is an open-source desktop app that runs several coding agents (Claude Code, Codex, OpenCode and any other terminal agent) side by side, each in its own git worktree, with one CLI to script it. Use when the user wants to race agents on the same task, hand work to another… - 100orca-cli
Operate Orca-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Orca's embedded browser through the `orca` CLI. Use when the user says "$orca-cli", "Orca worktree", "child worktree", "spawn codex/claude in a… - 90orca
The front door of Orca Strator. Checks the setup, changes the settings with buttons, and starts this session in the right role (orchestrator, lane, checker, or just this session), so nobody has to remember which orca command comes first. Also shows a status screen and every orca… - 100orca
Use when the user asks to run an Orca flow (e.g. "use orca to implement …"), or when delegating a well-defined implementation task to Orca's autonomous multi-agent flow — a headless plan-code-review CLI to hand a coding task to instead of implementing it yourself.