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 agent-native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.
| name | agent-native |
| description | Operate explicit orchestrator, implementer |
Operate caller-selected agent sessions as explicit roles without turning the runtime into AgentOps lifecycle authority.
For caller-elected multi-model judgment (mixed council, dueling perspectives,
cross-model validate), follow
references/model-dispatch.md: the working
session is the controller; probe codex-exec and ntm at runtime; never
require either; never use Agent Mail for judgment; never invoke claude -p.
Role separation works because each role's authority is checkable from its packet: a worker that cannot exceed its declared subject cannot corrupt a sibling's evidence, so factory failures stay local instead of systemic.
When a worker looks stuck, score interventions by evidence and reversibility before acting: observe more (free, fully reversible), then nudge, then replace the worker, then restart the runtime — escalate only when observable state, not impatience, rules out the cheaper step. Stop the observe-nudge cycle once the worker reaches a terminal status or the caller's observation window ends; past that point further intervention manufactures noise, not evidence.
Named failure mode — prompt-send optimism: treating a successfully delivered prompt as a working worker; delivery proves transport, not engagement.
Anti-pattern: restarting an unresponsive worker as the first move. Corrective: capture its observable state first — a restart destroys the evidence of why it stalled, and rescue is usually cheaper than rerun.
verdict.v2.NTM, Codex exec, native processes, Agent Mail, and Gas City are replaceable adapters. Use them only when the caller selected that execution shape. A single local agent pays no factory coordination cost. Model identity, when recorded, is a declared runtime fact like context identity — see references/model-dispatch.md.