Agentlas Core Engine Meta-Agent
SkillAI & modelsOnce this skill is added, your AI can build agents for Agentlas on your behalf. It can create a single agent, assemble a team of agents that work together, or take an agent you already have and fit it into the Agentlas setup. It is also what your AI uses for /meta-agent requests.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding it, ask your AI to create an agent or a team of agents, or send a /meta-agent request to get started.
Then ask your AI: use the Agentlas Core Engine Meta-Agent skill
What your AI can do with it
- Create a single Agentlas agent
- Build a team of agents that work together
- Package an agent that runs on your machine into the Agentlas setup
- Package an agent from somewhere else into the Agentlas setup
- Carry out /meta-agent requests
What this skill tells your AI
The instructions your AI receives, as published by agentlas-ai/agentlas-os in .agents/skills/agentlas-core-engine-meta-agent/SKILL.md and read by ahel’s review.
Procedure
- Read
AGENTS.md. - Read
.agentlas/mode-map.json. - Run mode classification.
- Ask clarify questions when missing details change files, adapters, or public/private boundary.
- Pick one team member:
- Single Agent Builder;
- Multi Agent Team Builder;
- Agentlas Packager.
- Load only the matching support skills.
- Emit or repair the Agentlas contracts, including
.agentlas/global-commands.json. Include.agentlasauto-activation seed files when local continuity is part of the output. - Write all generated or repaired runtime agent instructions in English, including adapters, role prompts, skills, handoff contracts, return contracts, and operating docs. Translate Korean or other-language source material into English agent behavior. Localized public copy and routing trigger examples may use the target user language.
- Add the generated command to Codex, Codex, Gemini CLI, generic AGENTS.md, and terminal adapters. For teams, expose the orchestrator/HQ command and route workers through HQ unless direct worker commands were requested.
- Verify with
scripts/verify-package.sh.
Output
Return status, evidence, output, global_commands, and blockers.
Signals
- GitHub stars
- 1k
- Forks
- 103
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
agentlas-core-engine-meta-agent- Source
- github.com/agentlas-ai/agentlas-os