用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/hashgraph-online/awesome-codex-plugins --skill status命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Coordinate agents via the AMQ CLI for file-based inter-agent messaging. Use this skill whenever you need to send messages to another agent (codex, claude, or any named handle), check your inbox, drain queued messages, set up co-op mode between agents, join a swarm team, route messages across projects, or diagnose delivery issues. Also use it when you receive a message and need to know how to reply, inspect receipts, or handle priority. Covers any multi-agent coordination task where agents need to talk to each other — review requests, questions, status updates, decision threads, wake notifications, and orchestrator integration (Symphony, Kanban). For collaborative spec/design workflows specifically, prefer the /amq-spec skill which provides structured phase-by-phase guidance. Not intended for distributed systems design (RabbitMQ, Kafka), CI/CD pipelines, or single-agent tasks with no partner.
Parallel-research-then-converge design workflow between two agents. Use this skill when the user wants two agents to independently think through a design problem before aligning on a solution — "spec X with codex", "design X together", "both agents think through X", "brainstorm architecture together", "parallel research then joint proposal", "think through separately then align", "careful thought from both sides before coding", or any variation where the user wants collaborative design rather than just splitting implementation work. Also use this when you receive a message labeled workflow:spec and need to know the correct receiver-side protocol. Not for sending simple messages or reviews (use /amq-cli), implementing completed designs, or creating document templates.
Use when defining new features, product behavior, UI/component design, architecture choices, contract changes, or ambiguous medium/high-complexity work before implementation, or when the user asks to grill or pressure-test a plan or design.
基于 SOC 职业分类
| name | status |
| description | Show the current state of a run — stages, roles, write locks, and gates. |
Display the current state of the team's work.
Use the --progress flag for a compact, human-friendly view:
python3 <runtime>/agenteam_rt.py status --progress
If the user specifically asks for raw JSON state, use without --progress:
python3 <runtime>/agenteam_rt.py status
Display the progress view in a readable format:
AgenTeam Run: <run-id>
Task: <task description>
Profile: <profile or "full">
Status: <running|completed|failed|stopped>
Elapsed: <Nm Ss>
Stages:
research ✓ completed (0m 45s)
strategy ✓ completed (0m 30s)
design ✓ completed (1m 02s)
implement → verifying (1m 15s) [verify attempt 2/3]
test · pending
review · pending
Active Lock: dev
Last Event: stage_verified (implement) — fail, attempt 2
Attempt: implement-dev-a1 | thread_id: <codex-thread-id>
Last heartbeat: 12s ago | idle budget: 14m 48s remaining
Wall budget: 47m remaining | stop reason: (none)
The progress view includes elapsed times per stage, the current
verify attempt if applicable, and the most recent event for context.
When governance.adoption is present, include the high-signal governance
items in the readable status: open follow-ups/escalations, recorded tripwire
blocks or warnings, gate rejections, and criteria overrides. Do not ask the
user to inspect raw .agenteam/governance files for these summary facts.
For an active or interrupted attempt, always include thread_id (or
"unavailable"), last heartbeat and age, idle budget and wall budget remaining,
attempt/retry counts, PID liveness when known, and stop reason. Treat a stale
heartbeat as AT RISK, not as proof that the role failed.
If no run is found, show:
.agenteam/config.yaml or legacy agenteam.yaml exist?)$ateam:run to start a new task."✓ — completed→ — in progress· — pending✗ — failed/blocked