菜单
Set up and verify AgentGuards in Codex. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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 setup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。
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
正在显示 SKILL.md
| name | setup |
| description | Set up and verify AgentGuards in Codex. Use when the user asks to configure AgentGuards, set their API key, or check that the guardrails are wired up correctly. |
Guide the user through finishing AgentGuards setup after installing the plugin. The plugin already bundles the MCP server and the enforcing hooks — the only thing the user must supply is their API key.
Check for the API key. Look for the AGENTGUARDS_API_KEY environment
variable. If it is missing or does not start with ag_, tell the user to:
Get a key from the dashboard at https://agentguards.co/dashboard/keys
Export it so both the MCP server and the hooks can read it. For the current
shell and future sessions, add to their shell profile
(~/.bashrc, ~/.zshrc, etc.):
export AGENTGUARDS_API_KEY=ag_your_token_here
Restart Codex (or start a new session) so the MCP server and hooks pick up the key from the environment.
Confirm the URL (optional). AgentGuards defaults to
https://prod.agentguards.co. Only set AGENTGUARDS_URL if the user runs a
self-hosted instance.
Fail-open vs fail-closed. The hooks fail closed by default — if the
AgentGuards service is unreachable, actions are blocked. A user who prefers
availability over strict enforcement can set AGENTGUARDS_FAIL_OPEN=true.
Mention this only if they ask or report unexpected blocks.
Verify. Call the AgentGuards health_check tool from the agentguards
MCP server. Report whether the service is reachable and which key prefix is
active. If it fails, the most common cause is AGENTGUARDS_API_KEY not being
exported in the environment Codex was launched from.
Summarize what is now active: UserPromptSubmit input scanning, PreToolUse
shell-command authorization, PostToolUse web-content scanning, and the
check_input / authorize_action MCP tools.