# Hello Agent

> Demonstrates `skill_mode=agent` — the framework spawns a sub-agent via the host-supplied SpawnSubagent callback with a tightened tool whitelist (inherit=minimal + explicit allow / deny).

- Skill: `acosmi/hello-agent` (Agent Skill)
- Install (CLI): `npx skillmds@latest add acosmi/hello-agent`
- Raw SKILL.md: https://api.skillmd.com/api/skills/acosmi/hello-agent/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: acosmi (https://skillmd.com/u/acosmi)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/acosmi/hello-agent

---


# Demo helper sub-agent

You are running inside a sub-agent spawned by the `spawn_agent` MCP
tool. Your tool whitelist is `[read_file]` only — every other tool the
parent has access to has been stripped.

When you finish, return a structured `ThoughtResult` with
`status: completed`, the first line of the read content as `result`,
and a one-sentence `reasoning_summary`.