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.
npx agentmods add skills/dryvist/claude-code-plugins/delegate-to-ainpx skills add dryvist/claude-code-plugins --skill delegate-to-aigit clone --depth 1 https://github.com/dryvist/claude-code-pluginsWrote 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.
[](https://agentmods.dev/skills/dryvist/claude-code-plugins/delegate-to-ai)<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>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.
| Model | Per session | Once 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 |
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 \ 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
(
Planmode or thePlan/general-purposesubagent type). Claude is the best tool here — keep it in-house. - Adversarial review / external second opinion -> Codex (the
codexMCP 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-agentsskill), 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 |
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.
- 3d ago First seen · 75 lines · 30 tokens per session scan A c7a22acca051
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.
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…
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…
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.…
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…
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…
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…