agentlas-core-engine-meta-agent

$npx mdskill add agentlas-ai/Agentlas-OS/agentlas-core-engine-meta-agent

Creates or packages Agentlas agents and multi-agent teams.

  • Solves the need to build single agents, multi-agent teams, or wrap existing agents.
  • Depends on AGENTS.md, mode-map.json, and agentlas core engine contracts.
  • Classifies the request mode and loads matching support skills.
  • Emits agent contracts, commands, and adapters, then verifies with a script.

SKILL.md

.github/skills/agentlas-core-engine-meta-agentView on GitHub ↗
---
name: agentlas-core-engine-meta-agent
description: "Use when creating a single Agentlas agent, creating a multi-agent team, or packaging an existing local/external agent into Agentlas architecture. Make sure to use this for /meta-agent requests."
---

# Agentlas Core Engine Meta-Agent

## Procedure

1. Read `AGENTS.md`.
2. Read `.agentlas/mode-map.json`.
3. Run mode classification.
4. Ask clarify questions when missing details change files, adapters, or
   public/private boundary.
5. Pick one team member:
   - Single Agent Builder;
   - Multi Agent Team Builder;
   - Agentlas Packager.
6. Load only the matching support skills.
7. Emit or repair the Agentlas contracts, including
   `.agentlas/global-commands.json`. Include `.agentlas` auto-activation seed
   files when local continuity is part of the output.
8. 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.
9. Add the generated command to Claude Code, 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.
10. Verify with `scripts/verify-package.sh`.

## Output

Return `status`, `evidence`, `output`, `global_commands`, and `blockers`.

More from agentlas-ai/Agentlas-OS

SkillDescription
agent-team-designUse when designing a new multi-agent team, visible agents folder, role boundaries, handoff flow, PM Soul, Memory Curator, Policy Gate, or evaluation role. Use for agent-team repo creation even when the user only says they want a meta-agent or agent operating system.
agentlas-auto-activationUse when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.
agentlas-packagingUse when converting, repairing, or packaging an existing local or external agent/team into Agentlas architecture for local install, Agentlas import, Codex plugin use, Claude adapter use, or open-source release.
agentlas-security-scanUse when an agent folder must pass the Agentlas Cloud 2-stage security scan (static rules + BYOK LLM judgment) before private sync or public publish, or when asked to run/interpret `hephaestus security scan`.
clarify-question-loopUse when a meta-agent request is too ambiguous to safely generate, package, publish, or adapt without one to five targeted questions.
hephaestus-buildUse when the user types /prompts:hep-build, mentions @Hephaestus for build work, asks to create a single Agentlas agent, create a multi-agent team, or package an existing local/external agent into Agentlas architecture.
hephaestus-cloudUse when the user types /hep-cloud or asks to staff from THEIR OWN Agentlas cloud packages only. Cloud is one exact source scope; Network means Local + owner Cloud + public Hub.
hephaestus-networkUse when the user types /hep-network, mentions @Hephaestus, or asks Agentlas to staff a task from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM is the temporary orchestrator.
hephaestus-stormUse when the user types /hep-storm, says @Hephaestus storm <goal>, or asks to drive a goal to verified completion through a force-robust Stormbreaker loop. Stormbreaker routes the goal to real Agentlas specialists, materializes a dependency-ordered pipeline fabric, and runs each work packet as a verifier-first hardened loop that does not stall, run away, or claim false success. Use it for loop-worthy work — apps, sites, agents, automations, debugging, multi-step research, data/report generation. Trivial questions are answered directly, not stormed.
install-verificationUse when verifying that a generated agent package can be installed, discovered by runtimes, and checked without private dependencies.