delegate-to-ai

delegate-to-ai is a skill for Claude Code, Codex from dryvist/claude-code-plugins. It costs 30 tokens per session (760 once invoked), scanned A, original, Apache-2.0.

A task-routing guide that chooses between Claude subagents, Codex, or a local MLX model based on the kind of work and privacy needs. A subagent is a separate AI worker handling part of a task.

In plain words
What is it for?
Use it to route implementation and planning, adversarial reviews, consensus work, or private and offline tasks.
Why use it?
It helps avoid sending every task to the same model, especially when you need an independent review or must keep data offline.

Skill for Claude CodeCodex

Part of the ai-delegation plugin — 6 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/dryvist/claude-code-plugins/delegate-to-ai
Any agent
npx skills add dryvist/claude-code-plugins --skill delegate-to-ai
Clone the repo
git clone --depth 1 https://github.com/dryvist/claude-code-plugins

Made for: Claude Code, Codex.

Or install ai-delegation, the plugin that ships this one along with the rest of its 6 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 delegate-to-ai

README.md
[![agentmods](https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/delegate-to-ai.svg)](https://agentmods.dev/skills/dryvist/claude-code-plugins/delegate-to-ai)
Your own site
<a href="https://agentmods.dev/skills/dryvist/claude-code-plugins/delegate-to-ai"><img src="https://agentmods.dev/badge/skills/dryvist/claude-code-plugins/delegate-to-ai.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 760 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00030 $0.00760
Opus 5 $0.00015 $0.00380
Sonnet 5 $0.00006 $0.00152
Haiku 4.5 $0.00003 $0.00076

Measured 3d ago against content hash c7a22acca051, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

delegate-to-ai scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://127.0.0.1:11434/v1/chat/completions \
ai-delegation/skills/delegate-to-ai/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate to External AI

Picks the right executor when Claude-in-this-session is not the best tool: native Claude subagents for implementation and planning, Codex for an external/adversarial second opinion, and local MLX for private or offline work.

When to Delegate

  • Implementation / architecture / planning -> native Claude subagent (Plan mode or the Plan / general-purpose subagent type). Claude is the best tool here — keep it in-house.
  • Adversarial review / external second opinion -> Codex (the codex MCP tool or CLI). A genuinely different model catches what a Claude subagent won't.
  • Multiple independent perspectives / consensus -> dispatch several native subagents in parallel (see the superpowers:dispatching-parallel-agents skill), optionally adding Codex as one of the voices. Synthesize the results yourself.
  • Private / offline / cheap local task -> local MLX via llama-swap (below). No prompt leaves the machine.

Local MLX — direct call

Local models are named by capability role, not physical id. Roles resolve to the resident model via the ai-stack registry (~/.config/ai-stack/registry.json, written by nix-ai); never hardcode a physical model id — when the resident model changes, only the registry changes.

Call llama-swap directly (OpenAI-compatible, no gateway hop):

curl -s http://127.0.0.1:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model":"default","messages":[{"role":"user","content":"..."}]}'

Roles: default, quickest, coding, tool-calling, large-context, most-capable, oss. Pick the role that fits the task; the registry maps it to the physical model.

Route Selection

Task type Route Executor
Implementation native subagent general-purpose subagent
Architecture / planning native subagent Plan mode / Plan subagent
Adversarial review external model Codex (codex MCP)
Multi-perspective / consensus parallel subagents N native subagents (+ Codex)
Private / offline / quick local local MLX llama-swap :11434, capability role

Read the full file on GitHub · 75 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. 3d ago First seen · 75 lines · 30 tokens per session scan A c7a22acca051

Subscribe to this mod's changes

delegate-to-ai is a skill published in the GitHub repository dryvist/claude-code-plugins (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 30 tokens to every session and 760 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

rspec

This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…

hoblin/claude-ruby-marketplace · 125 tokens

activerecord

This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…

hoblin/claude-ruby-marketplace · 180 tokens

dragonruby

This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…

hoblin/claude-ruby-marketplace · 100 tokens

draper-decorators

This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…

hoblin/claude-ruby-marketplace · 131 tokens

mcp-server

This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…

hoblin/claude-ruby-marketplace · 98 tokens

ratatui-ruby

This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…

hoblin/claude-ruby-marketplace · 119 tokens