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 generate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 | generate |
| description | Regenerate .codex/agents/*.toml from agenteam.yaml and plugin defaults. |
Regenerate Codex-native agent files from the current configuration.
agenteam.yaml manuallypython3 <runtime>/agenteam_rt.py roles list
If this fails, the config has errors — show them and stop.
Role models should normally inherit the platform default. For any explicit pin,
compare it with codex debug models; warn about unavailable or deprecated
entries without rejecting values solely because a static AgenTeam list is old.
python3 <runtime>/agenteam_rt.py generate
Show what was generated:
Generated agents:
.codex/agents/architect.toml (updated)
.codex/agents/dev.toml (updated)
.codex/agents/reviewer.toml (updated)
.codex/agents/qa.toml (updated)
If custom roles were included, highlight them:
.codex/agents/security_auditor.toml (custom role)
Optionally show a summary of each generated agent's key fields
(name, model, can_write, participates_in) for user verification.
Display an omitted model as platform default, not as a missing setting.
If the user regenerated agents because roles are missing from the @ picker,
tell them to confirm the files now exist under .codex/agents/ in the current
project, then open a new thread or restart Codex so it reloads workspace agents.