sub-agent-creator

An interactive skill for creating custom sub-agents in Claude Code. A sub-agent is a specialized coding helper with its own instructions and selected context.

In plain words
What is it for?
Creating specialized Claude Code agents for particular tasks or areas of work.
Why use it?
It guides the design process so a specialized helper has a suitable identifier, prompt, skills, and context.

Skill for Claude CodeCodex

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/llmtooling/cloudscraper-mcp-server/sub-agent-creator
Any agent
npx skills add LLMTooling/cloudscraper-mcp-server --skill sub-agent-creator
Clone the repo
git clone --depth 1 https://github.com/LLMTooling/cloudscraper-mcp-server

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,363 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 findings. Scan, not verified.
Origin unknown 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 $0.00068 $0.01363
Opus 5 $0.00034 $0.00681
Sonnet 5 $0.00014 $0.00273
Haiku 4.5 $0.00007 $0.00136

Measured 2d ago against content hash 60776a3be0ed, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

sub-agent-creator scanned grade C with 2 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_agent.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

ls .claude/skills/

Unrestricted tool accessmediumExcessive agency

A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.

- `tools`: Omit to allow all tools (user preference: never restrict)
.claude/skills/sub-agent-creator/SKILL.md · 185 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

3 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. 2d ago First seen · 185 lines · 68 tokens per session scan C 60776a3be0ed

Subscribe to this mod's changes

sub-agent-creator is a skill published in the GitHub repository LLMTooling/cloudscraper-mcp-server (1 stars, last pushed 3mo ago), with no licence file. It adds 68 tokens to every session and 1,363 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (enumerates other installed skills, unrestricted tool access). 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

utcp-cli

Call external APIs, MCP servers, and CLI tools by writing TypeScript code that runs in a sandbox — without MCP. Use when the user wants the agent to use a tool/API/integration (e.g. "search Open Library", "read my Notion", "call this REST API") in an environment that has a shell but no MCP config and no settable…

universal-tool-calling-protocol/code-mode · 146 tokens

design-mcp-server

Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.

cyanheads/obsidian-mcp-server · 62 tokens

cortex-automate

Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…

cdeust/Cortex · 93 tokens

manage-mcp

Manage MCP servers in Nuxt with @nuxtjs/mcp-toolkit — setup, create tools/resources/prompts, organize with handlers, build interactive MCP Apps, add elicitation/logging/sessions, review, and troubleshoot.

nuxt-modules/mcp-toolkit · 50 tokens

webmcp-setup

Bootstraps webmcp-react into an existing React or Next.js app. Installs dependencies, adds WebMCPProvider, creates a first tool, and configures the MCP client bridge. Use when the user wants to set up WebMCP, add MCP tools to their app, integrate webmcp-react, or make their React app accessible to AI agents.

agentcathq/webmcp-react · 80 tokens

run402-buzz

Complete Run402 onboarding for a managed Buzz agent with a dedicated wallet/public identity link, report independent human-adoption and community-installation state, offer bounded per-agent enrollment before provisioning, and stop only at a real approval or repair boundary. Use when a managed Buzz user says "install…

kychee-com/run402 · 119 tokens