# Managed Agent Intake

> Managed-agent front example; a governed agent-task that drafts a triage summary.

- Skill: `runxhq/managed-agent-intake` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add runxhq/managed-agent-intake`
- Raw SKILL.md: https://api.skillmd.com/api/skills/runxhq/managed-agent-intake/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: runxhq (https://skillmd.com/u/runxhq)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/runxhq/managed-agent-intake

---

# Triage intake

Read the issue inputs and produce a short triage summary. When the task is
complete, return the structured result.

By default the runtime yields this act to the host (`needs_agent`). If a managed
agent provider is configured (`runx config set agent.provider anthropic`, plus
`agent.model` and `agent.api_key`), the runtime drives the bounded tool-use loop
in-process instead, governed and sealed the same way.