agent-management

92 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By autonomous-ai/lampOS (GitHub) · coding · 554 stars · scanned at commit 9281ff9

Legacy Autonomous Buddy control for explicitly requested Buddy coding sessions. When the user asks a coding or research agent on their paired Harness computer to work, use harness-use instead. This manages explicit Buddy desktop CLI sessions; clicking apps and screenshots use computer-use.

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.

Found in 1 place.

skills/agent-management/SKILL.md, line 20python3 scripts/buddy_agents.py voice - <<'JSON'

Connects to the internet

The author does not mention this.

Found in 8 places.

skills/agent-management/scripts/buddy_agents.py, line 7import urllib.request
skills/agent-management/scripts/buddy_agents.py, line 43request = urllib.request.Request(endpoint, data=body,
skills/agent-management/scripts/buddy_agents.py, line 45opener = urllib.request.build_opener(urllib.request.ProxyHandler({}))

Show 5 more

skills/agent-management/scripts/voice_router.py, line 125prior = requests.get(request_id) if operation == "send" else None
skills/agent-management/tests/test_buddy_agents.py, line 16with self.subTest(action=action, params=params), patch.object(client.urllib.request, "build_opener") as opener:
skills/agent-management/tests/test_buddy_agents.py, line 26with self.subTest(body=body), patch.object(client.urllib.request, "build_opener") as build:
skills/agent-management/tests/test_buddy_agents.py, line 39with self.subTest(data=data), patch.object(client.urllib.request, "build_opener") as build:
skills/agent-management/tests/test_buddy_agents.py, line 48with patch.object(client.urllib.request, "build_opener") as build:

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'agent-management' ] || [ -L ~/.agents/skills/'agent-management' ]; then echo 'A skill folder named agent-management already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/autonomous-ai/lampOS' "$d" && git -C "$d" checkout --quiet '9281ff98f3f9e74a0fbf3a635298414fd449d344' -- 'skills/agent-management' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/agent-management' ~/.agents/skills/'agent-management' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'agent-management' ~/.claude/skills/'agent-management' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for autonomous-ai/lampOS shows the score of its lowest-scoring skill.

SkillTrust badge for autonomous-ai/lampOS

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/autonomous-ai/lampOS.svg)](https://zalavijaysinh.github.io/skilltrust/repos/autonomous-ai/lampOS/)

Score history

Date	Version	Score
2026-11-11	`9281ff9`	92