subagent-creator

subagent-creator is a skill for Claude Code from GzuPark/claude-plugin-pack. It costs 40 tokens per session (1,406 once invoked), scanned A, original, MIT.

A skill for creating specialized Claude Code sub-agents with custom instructions and tool settings. Sub-agents are task-focused AI workers defined in Markdown files.

In plain words
What is it for?
Use it to define project or user sub-agents, choose their tools and model, set permission behavior, and attach other skills.
Why use it?
It turns a repeated or specialized workflow into a reusable agent with a clear role, trigger, model, permissions, and available tools.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the creators plugin — 4 skills shipped together

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 skills/gzupark/claude-plugin-pack/subagent-creator
Any agent
npx skills add GzuPark/claude-plugin-pack --skill subagent-creator
Clone the repo
git clone --depth 1 https://github.com/GzuPark/claude-plugin-pack

Made for: Claude Code.

Or install creators, the plugin that ships this one along with the rest of its 4 skills.

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 subagent-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/gzupark/claude-plugin-pack/subagent-creator.svg)](https://agentmods.dev/skills/gzupark/claude-plugin-pack/subagent-creator)
Your own site
<a href="https://agentmods.dev/skills/gzupark/claude-plugin-pack/subagent-creator"><img src="https://agentmods.dev/badge/skills/gzupark/claude-plugin-pack/subagent-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,406 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 5.1 $0.00040 $0.01406
Opus 5 $0.00020 $0.00703
Sonnet 5 $0.00008 $0.00281
Haiku 4.5 $0.00004 $0.00141

Measured 6d ago against content hash 85213132b00d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

subagent-creator 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 6d 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.

plugins/creators/skills/subagent-creator/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-agent Creator

Create specialized AI sub-agents for Claude Code that handle specific tasks with customized prompts and tool access.

Sub-agent File Format

Sub-agents are Markdown files with YAML frontmatter stored in:

  • Project: .claude/agents/ (higher priority)
  • User: ~/.claude/agents/ (lower priority)

Structure

---
name: subagent-name
description: When to use (include "use proactively" for auto-delegation)
tools: Tool1, Tool2, Tool3  # Optional - inherits all if omitted
model: sonnet               # Optional - sonnet/opus/haiku/inherit
permissionMode: default     # Optional - default/acceptEdits/plan
skills: skill1, skill2      # Optional - auto-load skills
---

System prompt goes here. Define role, responsibilities, and behavior.

Configuration Fields

Field Required Description
name Yes Lowercase with hyphens
description Yes Purpose and when to use (key trigger)
tools No Comma-separated tool list
model No sonnet, opus, haiku, or inherit
permissionMode No default, acceptEdits, plan, etc.
skills No Skills to auto-load
hooks No Hooks for lifecycle (PreToolUse, etc.)

Creation Workflow

  1. Gather requirements: Ask about purpose, when to use, and capabilities
  2. Choose scope: Project (.claude/agents/) or user (~/.claude/agents/)
  3. Define configuration: Name, description, tools, model
  4. Write system prompt: Clear role, responsibilities, and output format
  5. Create file: Write the .md file to the appropriate location

Writing Effective Sub-agents

Description Best Practices

The description field is critical for automatic delegation:

# Good - specific triggers
description: Expert code reviewer. Use PROACTIVELY after writing code.

# Good - clear use cases
description: Debugging specialist for errors, test failures, unexpected behavior.

# Bad - too vague
description: Helps with code

Read the full file on GitHub · 196 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 196 lines · 40 tokens per session scan A 85213132b00d

Subscribe to this mod's changes

subagent-creator is a skill published in the GitHub repository GzuPark/claude-plugin-pack (6 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 1,406 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens