delegate

delegate is a skill for Claude Code, Codex from Magnus-Gille/claude-skills. It costs 75 tokens per session (2,331 once invoked), scanned A, original, MIT.

A way to send a small, self-contained task to a cheaper one-time AI runtime through Hugin's broker. It is intended for tasks such as summarizing, extracting information, classifying, drafting, or rewriting.

In plain words
What is it for?
Useful for sending a bounded prompt and receiving one result for routine text transformations; it is not intended for autonomous repository or git work.
Why use it?
It helps reserve larger agent runtimes for work that needs tools, files, code changes, or multiple steps.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions Codex.

Good fit Useful for sending a bounded prompt and receiving one result for routine text transformations; it is not intended for autonomous repository or git work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magnus-gille/claude-skills/delegate
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.

Any agent
npx skills add Magnus-Gille/claude-skills --skill delegate
Clone the repo
git clone --depth 1 https://github.com/Magnus-Gille/claude-skills

Made for: Claude Code, Codex.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/magnus-gille/claude-skills/delegate/github.svg)](https://agentmods.dev/skills/magnus-gille/claude-skills/delegate)
Your own site
<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/delegate"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/delegate/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 delegate

Your own site · 80×15
<a href="https://agentmods.dev/skills/magnus-gille/claude-skills/delegate"><img src="https://agentmods.dev/badge/skills/magnus-gille/claude-skills/delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,331 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 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 $0.00075 $0.02331
Opus 5 $0.00037 $0.01166
Sonnet 5 $0.00015 $0.00466
Haiku 4.5 $0.00007 $0.00233

Measured 12d ago against content hash 7447d9888785, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

delegate 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 12d 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.

delegate/SKILL.md · 187 lines

How it starts

The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/delegate — Delegate to a Cheaper Runtime

Hand a bounded task off to Hugin's broker (/v1/delegate/*) via the hugin-mcp MCP server. The broker dispatches to a cheaper one-shot runtime (Ollama on the Pi, or OpenRouter) and returns a single response. This is not the same as /submit-task — that runs a full agent (Claude Code / Codex) on the Pi for autonomous, multi-step work.

When to use which

Use /delegate when… Use /submit-task when…
One-shot transformation: summarize, extract, classify, draft, rewrite Multi-step autonomous work — code changes, commits, multi-tool reasoning
You want to save Claude tokens on routine work The task needs tool use, file I/O, MCP access, git
Bounded prompt → bounded response Open-ended "go figure this out"
Fast turnaround (seconds–minute) Long-running (minutes–hours)

If the task needs a worktree / git / file edits, use /submit-task instead — pi-large-coder exists in the alias map but isn't wired in v1.

Model check

If the current model is Opus, ask the user to run /model sonnet first. This skill is prompt-shaping plus MCP calls — Sonnet is enough.

Prerequisites

hugin-mcp must be registered as an MCP and connected. Check with claude mcp list. If absent, the user needs to register it (see Hugin's CLAUDE.md for the command and the broker token).

If the MCP is registered but the broker is unreachable, hugin_submit will return a broker_network_error — surface that clearly and stop.

Usage

  • /delegate — interactive: ask what to delegate
  • /delegate <description> — build a task from the description, confirm, submit

Flow

Step 1: Understand the task

If the user gave a description, paraphrase it back in one line and identify:

  • What's the input? (text, list, document — paste it inline if small, otherwise reference)
  • What's the desired output? (a summary, a JSON list, a draft email, a rewritten paragraph)
  • What's the format? (paragraph, bullets, JSON, etc.)

Read the full file on GitHub · 187 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. 12d ago First seen · 187 lines · 75 tokens per session scan A 7447d9888785

Subscribe to this mod's changes

delegate is a skill published in the GitHub repository Magnus-Gille/claude-skills (5 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 2,331 once invoked, about $0.0004 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

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens