create-agent

create-agent is a command for Claude Code from appboypov/pew-pew-plaza-packs. It costs 19 tokens per session (15,460 once invoked), scanned A, a copy of agent-conventions, MIT.

A command for designing and creating a specialized software agent from stated requirements. It produces the agent's configuration, instructions, permissions, and command entry point.

In plain words
What is it for?
Use it to define an agent's role, requirements, tools, security settings, delegation rules, and system prompt.
Why use it?
It gives a structured way to turn an idea into an agent that follows the project's conventions and has a clearly limited purpose.

Command for Claude Code

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

Good fit Use it to define an agent's role, requirements, tools, security settings, delegation rules, and system prompt.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/appboypov/pew-pew-plaza-packs/agent"><img src="https://agentmods.dev/badge/commands/appboypov/pew-pew-plaza-packs/agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 15,460 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 92% 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 $0.00019 $0.15460
Opus 5 $0.00010 $0.07730
Sonnet 5 $0.00004 $0.03092
Haiku 4.5 $0.00002 $0.01546

Measured 9d ago against content hash 3703ca790d36, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

create-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 9d 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

92% identical to agent-conventions — 568 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/plx/create/agent.md · 1,908 lines

How it starts

The opening of the file, as written. The whole thing — 1,908 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Command

When this command is used, check if any required information is missing. If so, ask the user to provide it. Otherwise, proceed with the request.


🤖 Create Agent: Design Specialized Sub-Agent from Requirements

💡 Transform requirements into a focused, single-purpose agent through systematic analysis and validation.

🎯 End Goal

💡 The clean, measurable objective that determines whether any following section provides value.

Successfully create a production-ready agent that:

  • Serves a single, well-defined purpose
  • Follows all agent conventions and patterns
  • Integrates seamlessly with Claude Code framework
  • Maintains appropriate tool security
  • Can operate autonomously within its scope
  • Is immediately usable via /act: command

📋 Request

💡 Verb-first activity request with optional deliverables and acceptance criteria

Create a new agent based on user requirements through systematic analysis and iterative refinement.

Deliverables

  • Complete agent file with all required sections
  • Proper YAML frontmatter configuration
  • Validated tool access specification
  • Clear delegation description
  • Comprehensive system prompt

Acceptance Criteria

  • Single responsibility clearly defined
  • All template sections present
  • Follows naming conventions
  • WikiLinks validated
  • Security considerations addressed
  • Output format specified

🔄 Workflow

💡 Systematic methodology for agent creation.

🌊 Agent Workflow: Systematic Sub-Agent Creation

💡 Transform requirements into focused, single-purpose agents through systematic decomposition and validation.

The agent workflow represents a sophisticated orchestration for creating specialized sub-agents that enhance Claude Code capabilities. This systematic approach ensures each agent maintains focused expertise, appropriate tool access, and seamless integration with the broader framework. Through hierarchical phases and quality gates, we transform abstract requirements into production-ready agents that operate autonomously within their defined scope.

Read the full file on GitHub · 1,908 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. 9d ago First seen · 1,908 lines · 19 tokens per session scan A 3703ca790d36

Subscribe to this mod's changes

create-agent is a command published in the GitHub repository appboypov/pew-pew-plaza-packs (85 stars, last pushed 8mo ago), licensed MIT. It adds 19 tokens to every session and 15,460 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to agent-conventions, differing in 568 lines, and is treated as a copy.