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 skills add redhuntlabs/wizard --skill building-a-subagent-spellgit clone --depth 1 https://github.com/redhuntlabs/wizardWrote 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/redhuntlabs/wizard/building-a-subagent-spell)<a href="https://agentmods.dev/skills/redhuntlabs/wizard/building-a-subagent-spell"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/building-a-subagent-spell.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 5.1 | $0.00038 | $0.01314 |
| Opus 5 | $0.00019 | $0.00657 |
| Sonnet 5 | $0.00008 | $0.00263 |
| Haiku 4.5 | $0.00004 | $0.00131 |
Grade A, and why
building-a-subagent-spell 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building a Subagent Spell
What this does
Specialist builder for kind: subagent spells. A subagent spell dispatches one or more helper agents — each with no context but what you hand it — and aggregates their results.
Used when: the work has independent pieces that can run in parallel, or when the work needs isolation from the main conversation.
When to use
- Routed to from
building-a-spellStage 2 whenkind: subagent - User describes work that has multiple independent parts ("research these 5 things", "review each chapter separately")
What you bring (Inputs)
- The task that has independent parts
- The unit of work each subagent will handle
- The aggregation strategy (how to combine results)
What you get (Output)
A draft SKILL.md with explicit Parallelism, Context handed to each subagent, Aggregation, and Partial-failure handling sections.
How it works (Steps)
This is a workflow.
Stages
Stage 1: Identify the unit of independence
Ask the user: "What's the smallest piece that one helper could do alone, given just the task and a few sentences of context?"
If you can't name it, this isn't a subagent kind. Re-route.
If the units depend on each other, name the dependency — you may need to dispatch in waves rather than all in parallel.
Stage 2: Decide parallelism
| Pattern | When |
|---|---|
| All-parallel | Units are fully independent (5 different companies to research) |
| Wave-parallel | Units have a partial order (research 5 companies, then compare top 3) |
| Serial | Each unit's output influences the next; consider if this is really a workflow kind |
Document the chosen pattern in ## Parallelism.
Stage 3: Declare context-flow EXPLICITLY
Subagents are stateless. They get only what you hand them. This is the section users get wrong most often.
Write ## Context handed to each subagent as a literal list:
## Context handed to each subagent
Each subagent receives EXACTLY:
1. <field 1>: <description>
2. <field 2>: <description>
3. <field 3>: <description>
Each subagent does NOT receive:
- The user's full conversation history
- Other subagents' progress or outputs
- Any state from prior dispatches in this session
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.
- 8d ago First seen · 170 lines · 38 tokens per session scan A bdd8bbf91b5a
building-a-subagent-spell is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 38 tokens to every session and 1,314 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.
Other skills, from other repositories
fastapi
A Python framework for building web APIs, which are interfaces that let programs communicate over HTTP. It supports request validation, automatic API documentation, asynchronous code, reusable dependencies, and common authentication methods.
fzf
A command-line tool for finding items by typing partial text, with results updating as you type. It can search files, shell command history, processes, directories, Git branches, commits, and other text output.
glances
A guide for using Glances, a cross-platform system-monitoring tool that displays computer resource and process information in a terminal, browser, or API.
lazydocker
A keyboard-driven terminal interface for managing Docker, a system for running applications in isolated containers.
paper-checking
A Windows application for finding copied text in documents. It compares files with a reference collection or compares documents in the same batch with one another.
you-get
A command-line tool for downloading videos, audio, and images from websites such as YouTube and Bilibili.