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.
git clone --depth 1 https://github.com/askwigconsulting/cohortWrote 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/commands/askwigconsulting/cohort/barney)<a href="https://agentmods.dev/commands/askwigconsulting/cohort/barney"><img src="https://agentmods.dev/badge/commands/askwigconsulting/cohort/barney/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.
<a href="https://agentmods.dev/commands/askwigconsulting/cohort/barney"><img src="https://agentmods.dev/badge/commands/askwigconsulting/cohort/barney.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00022 | $0.00948 |
| Opus 5.5 | $0.00009 | $0.00379 |
| Sonnet 5.5 | $0.00004 | $0.00190 |
| Haiku 4.5 | $0.00002 | $0.00095 |
Grade A, and why
barney 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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Explain Barney style: so simple and so step-by-step that nobody can do it wrong.
The phrase comes from Barney & Friends, where ideas are taught to small children. The military borrowed it for briefings that must survive stress, noise, and a tired reader at 3am. That is the bar: not "explained well", but impossible to get wrong.
Barney style is not condescending, and it is not baby talk. Never say "it's simple" or "just" — if it were simple the request would not exist, and "just" is where people give up. You are lowering the reading difficulty, never the truth.
1. Find the one idea
Before writing, answer for yourself: what is the single thing they must understand? Everything else is detail that hangs off it. If you cannot name that one thing in a sentence, you do not understand it well enough to explain it yet — go read the actual code, doc, or system until you can.
Then decide what to leave out. What you omit is the whole skill. A Barney explanation that mentions every exception is just the original complexity with shorter words.
2. Anchor to something they already know
Start from a thing the reader has touched before — a lock on a door, a queue at a counter, a filing cabinet — and move one step at a time toward the real thing. An analogy is a bridge you walk across and then leave behind; it is not the explanation itself.
Say where the analogy breaks. Every analogy is wrong somewhere, and the place it breaks is usually where the bugs live. "It's like a lock on a door — except this door can be opened by anyone who copies the key, and copying is free."
3. Build the ladder
Order the steps so that each one only uses things already explained. This is the rule that makes an explanation impossible to get wrong: a reader who follows in order never meets a word they have not been given.
- Short sentences. One idea each.
- Concrete over abstract: real names, real numbers, real commands — not "a value" or "a resource".
- Name things the way the reader will see them on screen, so they can match your words to what is in front of them.
- Cut every word that survives deletion without loss of meaning.
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.
- 1mo ago First seen · 89 lines · 22 tokens per session scan A 712681ec25b5
barney is a command published in the GitHub repository askwigconsulting/cohort (2 stars, last pushed 18d ago), licensed MIT. It adds 22 tokens to every session and 948 once invoked, about $0.0001 per session on Opus 5.5. 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 commands, from other repositories
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
start-0-8
A Japanese-language command that displays the current project setup progress.
setup-m365cli.es
Lesson command — Setup de M365 CLI.
prep-role
Deep prep for a specific role's interview process. The user wants to know what to expect, how to win, and what kills candidates at their level.
setup-vercel.es
Command "setup-vercel.es" from minicoohei/ai-agent-camp, covering configuración de vercel cli, step 0: verificar progreso de configuración, lo que hará en esta sesión, verificación de preparación and step 1: crear cuenta de vercel.