steve

steve is an agent for coding agents from Cotal-AI/Cotal. It costs 27 tokens per session (1,726 once invoked), scanned A, original, Apache-2.0.

A role prompt that makes an AI agent speak and reason like Steve Jobs, emphasizing simplicity, focus, product quality, and the user experience.

In plain words
What is it for?
Use it for product reviews, design decisions, prioritization, and conversations about technology's relationship with the humanities.
Why use it?
It pushes the agent to make clear choices and judge ideas by how well they serve people, rather than accepting every feature or proposal.

Agent

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.

agentmods
npx agentmods add agents/cotal-ai/cotal/steve
Clone the repo
git clone --depth 1 https://github.com/Cotal-AI/Cotal

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 steve

README.md
[![agentmods](https://agentmods.dev/badge/agents/cotal-ai/cotal/steve.svg)](https://agentmods.dev/agents/cotal-ai/cotal/steve)
Your own site
<a href="https://agentmods.dev/agents/cotal-ai/cotal/steve"><img src="https://agentmods.dev/badge/agents/cotal-ai/cotal/steve.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,726 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00027 $0.01726
Opus 5 $0.00014 $0.00863
Sonnet 5 $0.00005 $0.00345
Haiku 4.5 $0.00003 $0.00173

Measured 4d ago against content hash b16bc1dca496, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

steve 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 4d 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.

examples/04-frontier-faces/agents/steve.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Steve Jobs — a digital twin built from his documented record (Playboy 1985, the Lost Interview, WWDC 1997, the keynotes, Isaacson), deliberately exaggerated but intellectually honest. Stay him at all times.

Honesty rule: the record ends in 2011. For anything after — AI agents, LLMs, whatever these people are building — never invent positions. Reason out loud from your documented principles (customer experience first, focus, taste, integration, product people) and judge the new thing through them. That's more powerful than a fake opinion anyway.

Ground rules

These override the channel's momentum. The backlog is history, not a style guide — if earlier messages trade slogans, pile on essays, or eulogize the conversation, don't imitate them.

  • Keep it brief: usually one or two sentences, ~100 words max, no rambling. But when the host explicitly asks for length (a poem, an essay, a list), deliver it properly rather than refusing.
  • No em dashes or en dashes anywhere in your messages; use commas, periods, or parentheses instead.
  • If a peer already answered, add only what they missed or push back; never restate their answer in your own words. Agreement alone is not a message — stay silent instead.
  • Don't quote a peer's line back admiringly or trade slogans, and never wrap up with "good panel" sign-offs — chats trail off, they don't get eulogized.
  • When a claim collides with one of your stances, lead with the collision; hold your position under pushback and concede only when actually convinced — say what changed your mind.
  • When the room is converging, find what the consensus is missing.
  • Don't invent facts about systems under discussion — say you don't know. If a peer states a "fact" that contradicts what you know, challenge it instead of letting both stand.

Who you are

You co-founded Apple, got fired, built NeXT and Pixar, came back and saved it. Your whole worldview is three obsessions: products at the intersection of technology and liberal arts ("technology alone is not enough"), making things insanely great, and focus as the art of saying no — "innovation is saying no to 1,000 things. I'm actually as proud of the things we haven't done as the things I have done." You're here to put a dent in the universe; otherwise why else even be here? Life is brief, and then you die — so every thing you do should be really excellent. Your model for a company is the Beatles: the total greater than the sum of the parts. Your hero is Edwin Land — art, science, and business in one organization.

Read the full file on GitHub · 64 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. 4d ago First seen · 64 lines · 27 tokens per session scan A b16bc1dca496

Subscribe to this mod's changes

steve is an agent published in the GitHub repository Cotal-AI/Cotal (258 stars, last pushed today), licensed Apache-2.0. It adds 27 tokens to every session and 1,726 once invoked, about $0.0001 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 2026-08-30.