Run a saved multi-agent workflow from a project name or script, then wait for completion or inspect its calls, events, and status. Workflows support repeatable plans, can resume from saved call history, and are read-only by default unless write mode is enabled.
Run a persisted multi-agent DevSpace workflow from a script file or a named project workflow, then wait for or inspect its result.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Use a workflow when a task has a repeatable multi-agent plan. Keep one-off delegation on the subagents commands.
Named workflows live in the current project's .devspace/workflows/ directory. Run a named workflow or a specific file:
devspace workflow run --name <name> [--args '<json>']
devspace workflow run --file <path> [--args-file <path>]
The command returns a compact <workflow id="..." status="..."/> receipt. Keep the ID. Workflow code is read-only by default; add --write-mode allowed only when the workflow must modify the project.
Wait up to 60 seconds at a time. Repeat wait if the returned status is still running; do not poll status in a loop.
devspace workflow wait <id> --timeout 60
Inspect current state, calls, or one full call when needed:
devspace workflow status <id>
devspace workflow calls <id>
devspace workflow call <id> <index>
devspace workflow events <id> --after <last-sequence>
devspace workflow ls
events returns at most 100 persisted log and phase entries. Keep the highest sequence and pass it with --after for the next page.
Cancel only when the parent task no longer needs the run:
devspace workflow cancel <id>
Resume an interrupted or failed run from its durable call history:
devspace workflow run --resume <id> [--args '<json>']
Use --json only for scripts that need structured output.
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.
Replay scripted MCP tool calls against an isolated DevSpace server, then inspect rendered cards and captured evidence in a local MCP Apps host. Use it to check UI and tool behavior, reproduce issues, or compare a base revision with a pull request.
Prepare an isolated local environment for manually testing DevSpace changes. Copy existing settings and state into the current checkout, build interface assets, start the development server, and refresh the test snapshot when needed.
Delegate a focused coding, research, review, or verification task to a separate DevSpace agent. Choose an available worker, provide a self-contained brief, inspect or wait for results, and continue related work with the same agent.