axiopera 0.3.2

Orchestrate coding agents (Claude Code, Codex, Grok Build) as sub-agents of each other
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."
  axiopera spawn claude --tier read --name review -f task.md
  Tiers: read (read-only; requests needing approval are refused;
              MCP: read-only tools only, none on Grok; Grok shell: plain axiopera commands only),
         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.
  Tasks share your working directory unless --cwd selects another; axiopera creates no copy.
  Give parallel writers separate git worktrees via --cwd.
  A timeout interrupts the task; send resumes its session with a fresh time limit.
  axiopera models <agent> lists --model IDs and --effort values; --json includes descriptions.

Get results
  axiopera inbox           collects results, questions, approval requests and problems from
                           your sub-tasks. 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 After spawning or resuming tasks, run `axiopera watch --status` unless it is already running.
@codex Let your shell tool yield a background session so the user can see progress; the command
@codex exits when no tasks run. Receive results as directed by spawn.
@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.
  Messages confirmed as queued are handled in a following turn.
  Cancelled tasks can also resume with send or reply; their cancelled children stay stopped
  until continued separately.
  send --tier <read|work|full> changes permissions when idle.

Answer questions
  Sub-agents can keep working on independent work 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), ending the wait for approval.
  axiopera approve <request>      axiopera deny <request> --reason "Use a dry run instead."

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; --force to read it again
  axiopera cancel <task>    stop it and its children
  axiopera detach <task>    stop driving it and print the native command for the user