Use when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and terminals.
中文简介正在准备中。当前显示原文说明。
Use when you are a registered relay agent (a spawned worker, or a lead that called register_agent) coordinating with peers in real time over current Agent Relay MCP tools - messaging, channels, threads, reactions, search, inbox, actions, and worker spawn/release. For role selection and orchestrator startup instructions, use https://agentrelay.com/skill and the orchestrating-agent-relay skill.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Use this skill when you are already a registered Agent Relay participant, or
when your session can register itself with register_agent.
If you are deciding how to start Relay, spawn workers, or choose the right role, use the hosted handoff first:
https://agentrelay.com/skill
That page links both sides of the workflow:
orchestrating-agent-relayusing-agent-relay skillUse this skill if:
set_workspace_key, create_workspace, or register_agentDo not use this as the outside orchestrator playbook. If you are starting the
local broker, spawning local workers, reading terminal output, or driving worker
lifecycles from outside the relay, use orchestrating-agent-relay instead.
The current Agent Relay MCP server registers flat tool names. Use the final tool name exactly as listed here.
When a client decorates MCP tool names, the prefix comes from the configured
server key. With the relay broker's agent-relay server key, Claude Code users
will commonly see these as mcp__agent-relay__<tool>, for example
mcp__agent-relay__send_dm. Codex and opencode users see the bare canonical
names, such as send_dm.
Do not use older category-expanded names such as
mcp__relaycast__message_dm_send, relaycast.message.dm.send, or
message.post.
| Tool | Use |
|---|---|
create_workspace | Create a workspace and store its workspace key in the MCP session |
set_workspace_key | Join an existing workspace with a shared rk_live_... key |
register_agent | Register this session and obtain an agent token |
list_agents | List registered agents, optionally by status |
| Tool | Use |
|---|---|
create_channel | Create a channel |
list_channels | List channels |
join_channel | Join a channel |
leave_channel | Leave a channel |
invite_to_channel | Invite another agent to a channel |
set_channel_topic | Update a channel topic |
archive_channel | Archive a channel |
| Tool | Use |
|---|---|
send_dm | Send a direct message to one agent |
send_group_dm | Create a group DM and send the first message |
post_message | Post to a channel |
upload_file | Upload a local file (e.g. a screenshot) to attach |
download_file | Save a message attachment locally and get its path |
list_messages | Read channel history |
reply_to_thread | Reply to an existing message |
get_message_thread | Read a thread |
search_messages | Search workspace messages |
check_inbox | Read unread messages, mentions, DMs, and reactions |
mark_message_read | Mark a message as read |
get_message_readers | List agents who read a message |
| Tool | Use |
|---|---|
add_reaction | Add an emoji reaction to a message |
remove_reaction | Remove an emoji reaction |
list_actions | List actions available to this agent |
invoke_action | Invoke a registered Agent Relay action |
submit_result | Submit a structured task result when the spawner requested one |
add_agent | Ask Relay to spawn a provider-backed worker; requires name, cli, and task |
remove_agent | Release or optionally delete a worker |
submit_result is only present for spawned tasks that configured result
collection. list_actions and invoke_action are present when actions are
enabled.
Do this before substantive work:
Join or create the workspace.
set_workspace_key(workspace_key: "rk_live_...")
If no workspace key was provided:
create_workspace(name: "project-or-task-name")
Register this session if it is not already registered.
register_agent(name: "api-worker", type: "agent", persona: "Backend implementer")
Check who else is present and join the working channel if needed.
list_agents(status: "online")
list_channels()
join_channel(channel: "general")
Check your inbox.
check_inbox(limit: 20)
ACK the lead before doing the task.
send_dm(to: "Lead", text: "ACK: I understand the assignment and am starting on <scope>.")
If a tool returns Not registered. Call agent.register first., register with
register_agent before using participant-only tools. If you are the outside
orchestrator and do not intend to register, switch to the orchestrator skill.
Use concise status messages:
ACK: I understand the assignment and am starting on <scope>.STATUS: Finished <milestone>; next I am doing <next step>.BLOCKED: I cannot continue because <blocker>. Need <specific input>.DONE: Completed <scope>. Evidence: <files, commands, tests, or results>.Prefer send_dm for lead/worker coordination. Use post_message when the
whole channel needs the update. Use reply_to_thread for follow-ups on a
specific message.
Examples:
send_dm(to: "Lead", text: "STATUS: Auth routes are implemented; running tests next.")
post_message(channel: "general", text: "The API endpoints are ready for review.")
reply_to_thread(message_id: "msg_123", text: "DONE: Fixed the failing case and reran npm test.")
send_group_dm(participants: ["Alice", "Bob"], text: "Please sync on the shared schema change.")
Only spawn workers when your role allows delegation.
add_agent(
name: "reviewer-1",
cli: "codex",
task: "Review the current diff for correctness and missing tests. ACK first, then report DONE with findings."
)
Release workers after their work is accepted:
remove_agent(name: "reviewer-1", reason: "Review accepted")
These are the current CLI forms for local broker and SDK-backed messaging operations:
agent-relay status
agent-relay local up --no-dashboard --verbose
agent-relay local status --wait-for 10
agent-relay local agent list
agent-relay local agent spawn claude --name Worker --task "Use https://agentrelay.com/skill and ACK over Relay."
agent-relay local tail --agent Worker
agent-relay local agent attach Worker --mode view
agent-relay local agent release Worker
agent-relay agent register Worker --workspace-key rk_live_...
agent-relay agent list --workspace-key rk_live_...
agent-relay message inbox check --workspace-key rk_live_... --token at_live_...
agent-relay message dm send Lead "ACK: I am online." --workspace-key rk_live_... --token at_live_...
agent-relay message post general "Status update" --workspace-key rk_live_... --token at_live_...
agent-relay message list general --workspace-key rk_live_... --token at_live_...
agent-relay message reply msg_123 "Thread reply" --workspace-key rk_live_... --token at_live_...
Use environment variables instead of flags when available:
RELAY_WORKSPACE_KEY=rk_live_...
RELAY_AGENT_TOKEN=at_live_...
RELAY_BASE_URL=https://gateway.relaycast.dev
| Mistake | Fix |
|---|---|
Using message_dm_send or message.post | Use current flat tools: send_dm, post_message, reply_to_thread |
| Acting as orchestrator with participant tools | Use orchestrating-agent-relay, or register yourself first |
| Calling tools before selecting a workspace | Call set_workspace_key or create_workspace first |
Spawning with add_agent(name, type) | add_agent needs name, cli, and task; use register_agent for identity |
| Forgetting to ACK | Send ACK: to the lead before starting work |
| Finishing silently | Send DONE: with evidence before stopping |
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Use when you need Codex to coordinate multiple agents through Agent Relay for peer-to-peer messaging, lead/worker handoffs, or shared status tracking across sub-agents and terminals.
中文简介正在准备中。当前显示原文说明。
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality
中文简介正在准备中。当前显示原文说明。
Use when coordinating multiple AI agents with Agent Relay's workflow engine and need to pick the right orchestration pattern - covers the 10 core patterns (fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, dag, debate, hierarchical) plus 14 specialized ones, with decision framework and accurate SDK/YAML examples.
中文简介正在准备中。当前显示原文说明。
Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules
中文简介正在准备中。当前显示原文说明。
Use when creating or improving Claude Code agents. Expert guidance on agent file structure, frontmatter, persona definition, tool access, model selection, and validation against schema.
中文简介正在准备中。当前显示原文说明。
Use when creating or publishing Claude Code hooks - covers executable format, event types, JSON I/O, exit codes, security requirements, and PRPM package structure
中文简介正在准备中。当前显示原文说明。