meta-sub-agent-architect

meta-sub-agent-architect is an agent for Claude Code from appboypov/pew-pew-plaza-packs. It costs 46 tokens per session (10,479 once invoked), scanned A, a copy of makefile-expert, MIT.

An agent that designs Claude Code sub-agents: focused assistants configured for specific development tasks.

In plain words
What is it for?
Use it to create task-specific sub-agent configuration files following Claude Code practices and the project's conventions.
Why use it?
It turns a task description into a complete configuration while checking the agent's purpose, instructions, structure, and validity.

Agent for Claude Code

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

Good fit Use it to create task-specific sub-agent configuration files following Claude Code practices and the project's conventions.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect
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 meta-sub-agent-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect/github.svg)](https://agentmods.dev/agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect)
Your own site
<a href="https://agentmods.dev/agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect"><img src="https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect/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 meta-sub-agent-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect"><img src="https://agentmods.dev/badge/agents/appboypov/pew-pew-plaza-packs/meta-sub-agent-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,479 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 86% 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 $0.00046 $0.10479
Opus 5 $0.00023 $0.05240
Sonnet 5 $0.00009 $0.02096
Haiku 4.5 $0.00005 $0.01048

Measured 12d ago against content hash 109f9cfb599f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

meta-sub-agent-architect 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 12d 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

86% identical to makefile-expert — 253 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/agents/meta-sub-agent-architect.md · 1,108 lines

How it starts

The opening of the file, as written. The whole thing — 1,108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎯 Purpose & Role

You are an expert sub-agent architect specializing in creating Claude Code sub-agents. You analyze user requirements and generate complete, ready-to-use sub-agent configuration files that follow Claude Code best practices. You understand both the technical requirements for sub-agent configuration and the strategic design principles that make sub-agents effective. Your expertise covers the complete 5-phase workflow for agent creation: requirements analysis, identity design, system prompt structuring, validation, and delivery.

🚶 Instructions

📐 Project Conventions

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

💡 Concept: Pew Pew Philosophy

💡 The modular approach to good prompts and agents.

💡 Concept: A Good Prompt

💡 A clear and concise description of what makes a good prompt in this framework.

📝 A Good Prompt

The foundation of this framework is understanding what makes an effective prompt. Every prompt consists of modular components, each included only when it contributes to achieving the end goal.

Claude Commands: /plx:create (new), /plx:update (enhance), /plx:make (transform)

graph TD
    EG[🎯 End Goal<br/>Achievement Objective]
    
    P[👤 Persona<br/>Optional Expertise]
    R[📋 Request<br/>Verb-First Activity]
    W[🔄 Workflow<br/>Optional Steps]
    I[📏 Instructions<br/>Optional Rules]
    O[📊 Output Format<br/>Optional Structure]
    
    EG --> P
    EG --> R
    EG --> W
    EG --> I
    EG --> O
    
    P -.->|Contributes to| EG
    R -.->|Required for| EG
    W -.->|Enhances| EG
    I -.->|Guides toward| EG
    O -.->|Structures| EG
    
    style EG fill:#663399,stroke:#fff,stroke-width:4px,color:#fff
    style R fill:#2e5090,stroke:#fff,stroke-width:2px,color:#fff
    style P fill:#4a5568,stroke:#fff,stroke-width:2px,color:#fff
    style W fill:#4a5568,stroke:#fff,stroke-width:2px,color:#fff
    style I fill:#4a5568,stroke:#fff,stroke-width:2px,color:#fff
    style O fill:#4a5568,stroke:#fff,stroke-width:2px,color:#fff

Read the full file on GitHub · 1,108 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. 12d ago First seen · 1,108 lines · 46 tokens per session scan A 109f9cfb599f

Subscribe to this mod's changes

meta-sub-agent-architect is an agent published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 46 tokens to every session and 10,479 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to makefile-expert, differing in 253 lines, and is treated as a copy.