菜单
Run agent native.
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。
基于 SOC 职业分类
Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links. Use when automating signup, login, or email verification without parsing HTML manually.
Spin up isolated sandboxes ("boxes") for coding agents, run them in parallel, queue background runs with -i, and push commits safely through the host relay. Use when the user wants to run Claude Code / Codex / OpenCode in a sandbox, start more boxes, attach to a running box, or otherwise operate the `agentbox` CLI on their laptop.
Use when building an HTTP val — a web endpoint, API route, webhook receiver, or any val that responds to HTTP requests. Covers the handler signature, Hono usage, the endpoint URL, CORS behavior, redirects, and Val Town-specific limitations.
Use when creating a new val and choosing which starter to fork. Covers the catalog of official starter templates, which project shape each one fits, and when forking an existing val is the better starting point.
Switch coding-agent accounts on a usage/rate limit, routed by host and agent.
Use Agent Mail from Codex for file leases, notifications, inboxes, and conflict prevention.
| name | agent-native |
| description | Run agent native. |
Quick Ref: Run a Claude/Codex loop outside an interactive session (Managed Agent, Agent SDK, or self-hosted sandbox) under the same AgentOps guardrails — hooklessly. Guardrails = skills + the
aoCLI + CI, never ported hooks. Bundle skills into the agent definition, exposeaoas a callable tool so the loop self-bootstraps + self-validates, and gate the output through the SAME CI as interactive work.
Codex (gpt-5.3-codex) has NO Managed Agents API, NO Workflow tool, NO Task subagent. It orchestrates via ATM (tmux pane swarms + agent-mail) + skills + the ao CLI + ssh to bushido. ATM is Bo's fork/alias of upstream NTM: atm points at ~/dev/ntm/dist/atm-darwin-arm64 and preserves the upstream ntm command surface. So an out-of-session Codex loop becomes AgentOps-native the same way: load the AgentOps skills, call ao session bootstrap / ao inject / ao validate directly (no MCP needed — Codex shells out), and gate outputs through CI (agent-output-validate.yml). ao does not wrap gc; a whole loop needing a mayor/refinery still routes through gc.
Load and follow the skill instructions from the sibling SKILL.md — OR read skills/agent-native/SKILL.md in the host repo for the canonical specification. Honor the Critical Constraints: this is a reframe of "port hooks", NOT a hook revival; no skill fork (load the same skills/ files); Managed Agents are NOT ZDR (no holdout/PII in the agent definition); CI is the enforcement boundary, not the optional in-loop adapter.
