axiopera: run other coding agents (claude, codex, grok) as your sub-agents.
Use axiopera for a different agent or model, or for work that must continue after your
session ends.
Dispatch
axiopera spawn codex "Fix the failing test in tests/parser.rs; run cargo test before finishing."
axiopera spawn claude --tier read --name review -f task.md
Tiers: read (look, don't change; MCP: read-only tools only, none on Grok),
work (default: the agent's own auto mode), full (the agent's full-access mode).
Options: --model, --effort, --name (use it instead of the ID), --cwd, --timeout 30m.
axiopera models <agent> lists --model IDs and --effort values; --json includes descriptions.
Get results
axiopera inbox takes what your sub-tasks have for you: results, questions, approval
requests and problems. Each is handed over once. Never blocks.
axiopera wait blocks until there is something new, lists it, and takes nothing.
@claude Run `axiopera wait` as a background command (teammates of team-lead: foreground). When it
@claude exits, run `axiopera inbox`, and start `axiopera wait` again while sub-tasks still run.
@claude Native subagents and teammates share their parent's inbox,
@claude so all pass task IDs to wait and inbox.
@codex The output of spawn says how results reach you.
@grok Before you spawn, start `axiopera watch --caller grok:<session>` with your monitor tool,
@grok persistent, unless it is running; start it again if told it ended while sub-tasks run.
@grok For each line it prints, run `axiopera inbox`.
Exit codes: 0 success, 1 command error, 3 nothing new yet (or wait timed out),
4 nothing new and nothing running.
Continue a task
axiopera send <task> "Also update the docs." steers the running turn, or starts a new turn
in the same session if it already finished.
Results note when they may predate your message; late messages are handled in the next turn.
Add --tier full to change permissions when idle.
Answer questions
Questions arrive like results; sub-agents can keep working until you answer.
axiopera reply <question> "Use port 8080." reaches it mid-turn, or resumes it.
Approval requests pause the sub-agent until you decide; unanswered requests are denied
after the approval timeout (2 minutes by default) and the sub-agent goes on without it.
axiopera approve <request> axiopera deny <request> --reason "Use a dry run instead."
For long messages, use `send <task> -f msg.md` or `reply <question> -f answer.md`; use `-` to read stdin.
Sub-agents can talk to each other: give them each other's task IDs and tell them to run
`axiopera tell <task> "..."` (Codex sub-agents have it as the `tell` tool). You get a copy of
every note.
Inspect and stop
axiopera status your sub-tasks axiopera log <task> recent events
axiopera result <task> latest turn result axiopera cancel <task> stop it and its children
axiopera detach <task> hand it to the user: prints the native command to continue it