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 researching-five-things-in-parallelgit 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/researching-five-things-in-parallel)<a href="https://agentmods.dev/skills/redhuntlabs/wizard/researching-five-things-in-parallel"><img src="https://agentmods.dev/badge/skills/redhuntlabs/wizard/researching-five-things-in-parallel.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 | $0.00031 | $0.01037 |
| Opus 5 | $0.00015 | $0.00518 |
| Sonnet 5 | $0.00006 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00104 |
Grade A, and why
researching-five-things-in-parallel 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researching Five Things in Parallel
What this does
When you need to research N independent topics (5 companies before a sales call, 5 candidates before interviews, 5 papers for a literature scan), this skill dispatches one research subagent per topic in parallel, aggregates results, and returns a unified brief.
When to use
- Researching multiple companies, people, papers, products, or places — and the research is independent
- Pre-meeting prep when you have multiple counterparties
- Side-by-side comparison shopping
- Any "do this same thing for each of N items" research task
Do not use when
- Items depend on each other (e.g., "research X, then based on what you find, research Y") — use a workflow instead
- N = 1
- Items require different research methods each — dispatch separately by hand
What you bring (Inputs)
- The list of N items (max 8 recommended)
- The research question to apply to each (must be the same for all items)
- The target output format (table row, paragraph, slide)
- Any time constraint per item (default: 5 min per subagent)
What you get (Output)
A unified document where each item appears in the same format, plus a "compare" section that surfaces deltas across items.
How it works (Steps)
This is a subagent dispatch. For each item in the input list, one research-helper subagent is dispatched in parallel; the parent aggregates after all return.
Parallelism
All N subagents (max 8 recommended) run concurrently. Wall-clock time is bounded by the slowest single subagent plus aggregation, not the sum.
Context handed to each subagent
Each subagent receives EXACTLY:
- The single item (name + any identifier)
- The research question (verbatim, same for all)
- The output format (verbatim, same for all)
- The time budget (default 5 min)
- Permitted sources (e.g., "public web only" / "internal docs included" / "no AI-generated summaries")
Each subagent does NOT receive: the other items, their results, or your overall purpose.
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 · 109 lines · 31 tokens per session scan A 796b17df064e
researching-five-things-in-parallel is a skill published in the GitHub repository redhuntlabs/wizard (9 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,037 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.