amq-cli
Coordinate coding agents through AMQ. Use for agent messages, inboxes, receipts, sessions, wake delivery, cross-project routing, managed launches, or AMQ diagnostics. Use amq-spec for collaborative design; do not use this for general message queues or single-agent work.
How do I install this agent skill?
npx skills add https://github.com/avivsinai/agent-message-queue --skill amq-cliIs this agent skill safe to install?
- Gen Agent Trust Hubpass
This skill facilitates coordination between AI agents using the AMQ CLI, a file-based messaging system. It provides protocols for task routing, role assignment, and inter-agent collaboration across different sessions and projects. The skill includes integration hooks for orchestrators like Symphony and Cline Kanban and uses a structured environment configuration model.
- Socketpass
No alerts
- Snykwarn
Risk: MEDIUM · 2 issues
- Runlayerpass
2/4 files flagged
What does this agent skill do?
AMQ CLI
Use the amq CLI for all queue operations. Never edit Maildir files directly.
AMQ transports coordination; the caller or orchestrator still owns task planning,
worktrees, approvals, and delivery.
Start in the correct context
Inside coop exec, use the environment as provided and run bare amq commands.
Do not override --me or reconstruct the root. Outside it, resolve and export the
complete context before reading or sending:
amq_context="$(amq env --me "<handle>" --export)" && eval "$amq_context" &&
amq drain --include-body
For a named session, add --session <name> to amq env. Treat the evaluated
context as one terminal bound to one session. Use --session or --project for
deliberate routing; do not point a participating command at another queue with a
raw --root.
Receive under a live wake
If session-start context says wake=live(...), or
amq wake check --me <handle> --json reports live_wake: true with an
injection mode other than none, the wake delivers a doorbell for you.
Run amq drain --include-body when it fires, then act on the messages.
Do not run amq watch, amq monitor, sleep-poll, or start another inbox
watcher under that live wake. A blocking wait holds your turn while the
doorbell queues behind it. When your work is done, finish the turn; do not
keep a tool running or send idle check-ins just to wait for mail.
Without an injecting wake, use the receive methods in the operations guide.
A notify-only wake (--inject-mode none) paired with a supervisor monitor
service is a separate supported setup.
Route the task
| Need | Read or run |
|---|---|
| Send, reply, drain, inspect receipts, or diagnose | Use the operations guide. |
| Two-agent research and design | Use the amq-spec skill. |
| Co-op roles and phased collaboration | Read co-op mode. |
| Claude Code Agent Teams | Read swarm mode. |
| Cross-project delivery or decision threads | Read cross-project routing. |
| Grok Bot on a registered Mac | Read registered-machine execution. |
| Symphony or Kanban adapters | Read integrations. |
| Message schema details | Read message format. |
| Multi-round background review | Read review loop. |
| Attach to a running harness session | Read the amq-remote reference. |
Use amq <command> --help for current flags. The repository README is the
canonical setup path.
Remote
amq-remote is a companion binary, not an amq subcommand. It attaches to a
harness session that is already running. Targets are declared in
<AM_ROOT>/extensions/remote/manifest.json (claude, codex, amit, or
fake). up supervises the endpoint; submit, status, wait, and
cancel talk to it; share mints the session body key. A manifest relay
object shares a target with its owner over a Buzz relay. DM commands require
the pinned native_session_id and run only while that session is attached;
Desktop presence reports the attachment status and honors the pin when one
is set.
doctor lists each failing boundary under failing and exits 6 while any
remains. Flags and exit codes
are in the amq-remote reference. The design is
the remote-control ADR. Pinned seams are
the compatibility manifest.
Safety and delivery rules
- A wake notification is attention, not consumption proof. Use receipts or
--wait-for drainedwhen delivery proof matters. - Preserve the existing thread when replying. Drain again after a doorbell; the newest complete message body is authoritative.
- Cleanup is explicit through
amq cleanup. Do not add automatic deletion. - Before any wake mutation, run
amq wake check --me "<handle>" --json. Act only whenrestart_capability=agent_safe; otherwise preserve state and report the required operator action. - Keep cross-host payloads outside privileged inboxes until the configured bridge has authenticated and applied them. Never copy or remote-drain a foreign Maildir as a substitute for routing.
- Do not translate native Windows injection into Unix
wakeorcoop exec. Read the platform section in the operations guide when Windows is involved. - Dangerous provider bypass flags belong only on an operator-controlled direct
coop execcommand. Do not place them in committed launch configuration.
The full command catalog, environment precedence, setup flow, platform notes, operator gates, and examples are in the operations guide.
How can the creator link this skill?
Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.
<a href="https://skillzs.dev/skills/avivsinai/agent-message-queue/amq-cli">View amq-cli on skillZs</a>