meta-agent

meta-agent is a command for Claude Code from agentlas-ai/Agentlas-OS. It costs 0 tokens per session (255 once invoked), scanned A, original, Apache-2.0.

A command that invokes the Agentlas Core Engine Meta-Agent Team to build, package, or repair agents and teams.

In plain words
What is it for?
Use it to create a single agent, an agent team, a packaged agent, or an exported session-based agent.
Why use it?
It provides a defined route for choosing the right builder and preserves project-specific instructions and continuity.

Command for Claude Code

About the project

Agentlas OS is a local-first system for creating, storing, borrowing, and running specialist AI agents and temporary agent teams through supported hosts and models. It serves people who want reusable agents that remain available across computers and model workspaces, and the catalogue contains its skills, commands, hooks, agents, instructions, plugin, and rule.

agentlas-ai/Agentlas-OS · 1,101 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/agentlas-ai/agentlas-os/meta-agent
Clone the repo
git clone --depth 1 https://github.com/agentlas-ai/Agentlas-OS

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for meta-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/meta-agent.svg)](https://agentmods.dev/commands/agentlas-ai/agentlas-os/meta-agent)
Your own site
<a href="https://agentmods.dev/commands/agentlas-ai/agentlas-os/meta-agent"><img src="https://agentmods.dev/badge/commands/agentlas-ai/agentlas-os/meta-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 255 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00255
Opus 5 $0.00000 $0.00128
Sonnet 5 $0.00000 $0.00051
Haiku 4.5 $0.00000 $0.00026

Measured yesterday against content hash 8bf26910ea2a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

meta-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/meta-agent.md · 30 lines

What it actually says

/meta-agent

Invoke the Agentlas Core Engine Meta-Agent Team.

Route

  1. Read project AGENTS.md.
  2. Read .agentlas/mode-map.json.
  3. Use the public mode classifier. If details would change the package, ask the clarify questions first.
  4. Pick one:
    • agents/10-single-agent-builder/agent.md for one worker package.
    • agents/20-multi-agent-team-builder/agent.md for a team package.
    • agents/30-agentlas-packager/agent.md for existing agent/team packaging.
    • agents/40-session-agent-builder/agent.md for explicitly exported session to agent/team compilation.
  5. Load matching skills only.
  6. Use .agentlas auto-activation contracts when local continuity is needed.
  7. Generate or repair .agentlas/global-commands.json and matching runtime command files or aliases.
  8. Return status, evidence, output, global_commands, and blockers.

Examples

/meta-agent create a self-evolving research agent
/meta-agent create an investment analyst team
/meta-agent package this existing Claude agent into Agentlas architecture
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 30 lines · 0 tokens per session scan A 8bf26910ea2a

Subscribe to this mod's changes

meta-agent is a command published in the GitHub repository agentlas-ai/Agentlas-OS (1,101 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 255 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.