Aster Orchestration

---
name: aster-orchestration
description: >-
  Consult an existing Aster agent from the current chat and return its answer,
  or coordinate supervised Aster workers: threaded messages, blocking ask/reply,
  task dispatch, worker_done/escalation waits, task DAGs, decision gates,
  coordinator loops, and decomposing work across agents. Use `aster-cli` for full
  ownership handoffs — "hand off", "handoff", "handover", "give this to another
  agent", "another worktree" — unless asked to supervise, monitor, or coordinate
  a DAG, and for terminal control, lightweight terminal prompts, shell commands,
  Aster worktree management, and reading or waiting on terminals.
---

# Aster Orchestration

This file is a discovery stub, not the usage guide. The full, version-matched Aster
orchestration reference is served by the `aster` binary itself — kept out of this file on
purpose so it can never drift from the binary that will actually run your commands.

Engage Aster orchestration whenever you need structured multi-agent coordination: threaded
messages, blocking ask/reply flows, task dispatch, worker_done/escalation waits, task DAGs,
decision gates, coordinator loops, or decomposing work across agents. Use the aster-cli skill
instead for full ownership handoffs ("hand off", "handoff", "handover", "give this to
another agent", "another worktree") when the user did not ask to supervise, monitor, wait
for results, or coordinate a DAG — and for ordinary terminal control, shell commands,
worktree management, and the built-in browser. Coordination requires real Aster runtime
state; never substitute a non-Aster subagent tool.

When a user asks from the current chat to consult a relevant existing agent and bring its
answer back, use this skill too. The user need not select a target chat first.

## 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. Aster exports this
  for managed WSL sessions.
- Otherwise, in a dev checkout whose session exposes `ORCA_DEV_REPO_ROOT`, use `aster-dev`.
- Otherwise, use `aster` (the same name on macOS, Linux, and Windows). Never substitute a
  similarly named command from another app.

Below, `ASTER` is a placeholder for the executable you resolved. Substitute it before
running anything; do not create a shell variable or run `ASTER` 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 Aster build.

## Load the version-matched guide before running Aster commands

```text
ASTER skills get aster-orchestration
```

That prints the compact, version-matched guide for the exact binary that will handle your
next commands. It covers the normal local coordinator loop. For a conditional action gate
such as remote placement, uncertain release recovery, or expanded DAG work, load only the
reference that gate names with
`ASTER skills get aster-orchestration --reference references/<file>.md`
(`--references` lists the names). If that binary rejects `--reference`, run
`ASTER skills get aster-orchestration --full` and read the named bundled reference before acting.

Prefer `--json`. Use the selected executable's `--help` for commands or flags the guide does
not cover. If a command reports that Aster is not running, start it with `ASTER 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 `ASTER open` or restart Aster. If
`skills get` is unknown, explain that updating Aster restores the guide; use `--help` for
read-only discovery and do not guess unsupported commands.