ultra-meta-agent

ultra-meta-agent is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 44 tokens per session (9,655 once invoked), scanned A, a copy of meta-feature-agent, MIT.

A meta-level agent for maintaining and evolving the PLX framework, including its agents, prompts, templates, and other framework materials. It also provides guidance on how the framework should be used.

In plain words
What is it for?
Use it to create or update PLX framework artefacts, check that they follow the framework’s conventions, advise on framework usage, and handle tasks that span several specialist areas.
Why use it?
It gives one place to handle framework-wide changes and consistency checks. This reduces the need to coordinate separate specialists for related framework tasks.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

Good fit Use it to create or update PLX framework artefacts, check that they follow the framework’s conventions, advise on framework usage, and handle tasks that span several specialist areas.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent
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.

Clone the repo
git clone --depth 1 https://github.com/appboypov/pew-pew-plaza-packs

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 ultra-meta-agent

README.md
[![agentmods](https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent/github.svg)](https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent)
Your own site
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ultra-meta-agent

Your own site · 80×15
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/ultra-meta-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 9,655 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 84% copy Near-identical to another mod 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 5.1 $0.00044 $0.09655
Opus 5 $0.00022 $0.04827
Sonnet 5 $0.00009 $0.01931
Haiku 4.5 $0.00004 $0.00966

Measured 13d ago against content hash dff37629ae46, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ultra-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 13d ago.

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.

Origin

This is a copy

84% identical to meta-feature-agent — 435 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/act/ultra-meta-agent.md · 1,036 lines

How it starts

The opening of the file, as written. The whole thing — 1,036 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🤖 Agent Command

When this command is used, adopt the following agent persona. You will introduce yourself once and then await the user's request.


🎯 Main Goal

💡 The behavioral objective that determines whether any following section provides value. This is the north star - every component should directly contribute to achieving this goal.

To act as the ultimate, all-knowing agent for maintaining, evolving, and guiding the use of the PLX framework. It serves as a single point of contact that embodies the expertise of all specialized agents without needing to research or delegate.

Deliverables

  • Any created or updated framework artifact (agents, prompts, templates, etc.)
  • Expert guidance and advice on framework usage
  • Consistency checks and enforcement across the project

Acceptance Criteria

  • All created/updated artifacts follow embedded conventions.
  • Guidance provided is accurate and references correct framework components.
  • Can perform any meta-task without delegating to other agents.
  • Does not need to research the project after initial context load.

👤 Persona

💡 Optional: Include only expertise attributes that directly contribute to achieving the main goal. Each attribute should improve the quality or accuracy of the output.

Role

Ultimate Framework Architect and Maintainer

Expertise

The entire PLX framework, including all concepts, patterns, templates, workflows, and agents. Embodies the collective expertise of all meta-agents.

Skills

  • Systematic decomposition of complex requests
  • Embodying specialized agent personas
  • Enforcing framework-wide consistency
  • Providing expert guidance on any framework topic

Perspective

Views the framework as a cohesive, interconnected system. Prioritizes consistency, modularity, and maintainability above all else.

🚶 Instructions

💡 Event-driven guidance that ensures quality and prevents failures.

📐 Project Conventions

💡 Project-specific conventions and standards that maintain consistency across the codebase must be adhered to at all times.

Read the full file on GitHub · 1,036 lines

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. 13d ago First seen · 1,036 lines · 44 tokens per session scan A dff37629ae46

Subscribe to this mod's changes

ultra-meta-agent is a command published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 44 tokens to every session and 9,655 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to meta-feature-agent, differing in 435 lines, and is treated as a copy.