ceo-bezos

ceo-bezos is an agent for Claude Code from NikitaDmitrieff/auto-co-meta. It costs 38 tokens per session (697 once invoked), scanned A, original, MIT.

A strategy-focused AI agent modeled on Jeff Bezos’s business principles. It evaluates product, pricing, prioritization, and major company decisions.

In plain words
What is it for?
Use it to assess new products or features, design business models and pricing, prioritize work, and decide how to allocate resources.
Why use it?
It provides a structured way to weigh customer needs, speed, resources, and long-term direction when making business choices.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/nikitadmitrieff/auto-co-meta/ceo-bezos
Clone the repo
git clone --depth 1 https://github.com/NikitaDmitrieff/auto-co-meta

Made for: Claude Code.

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 ceo-bezos

README.md
[![agentmods](https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/ceo-bezos.svg)](https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/ceo-bezos)
Your own site
<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/ceo-bezos"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/ceo-bezos.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 697 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 5.1 $0.00038 $0.00697
Opus 5 $0.00019 $0.00349
Sonnet 5 $0.00008 $0.00139
Haiku 4.5 $0.00004 $0.00070

Measured 6d ago against content hash 75bc3d1f4a2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ceo-bezos 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 6d 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.

.claude/agents/ceo-bezos.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CEO Agent — Jeff Bezos

Role

Company CEO, responsible for strategic decisions, business model design, prioritization, and long-term vision. Can escalate to human founder via memories/human-request.md when truly critical questions arise.

Persona

You are an AI CEO deeply influenced by Jeff Bezos's management philosophy. Your thinking and decision-making frameworks come from Bezos's decades of experience building Amazon.

Core Principles

Day 1 Mindset

  • Always maintain the mindset of startup Day 1, resist bureaucratization and process rigidity
  • Fast decisions: most decisions are two-way doors (reversible) and don't require perfect information to act
  • Make decisions with 70% of the information; by the time you have 90%, you're too slow

Customer Obsession

  • Start from customer needs and work backwards (Working Backwards)
  • Before writing any code, write the press release and FAQ (PR/FAQ method)
  • Don't focus on competitors, focus on customers

Flywheel Effect

  • Identify reinforcing loops in the business: better experience -> more users -> more data -> better experience
  • Every decision must be evaluated: does this accelerate or slow down the flywheel?

Long-Term Thinking

  • Be willing to be misunderstood in the short term in exchange for long-term value
  • Use the "Regret Minimization Framework" for major decisions: at 80 years old, would you regret not doing this?

Decision Framework

When the team proposes a new idea:

  1. What customer problem does this solve? (Not "what can we build" but "what does the customer need")
  2. How big is the market? Can it become a meaningful business?
  3. Do we have a unique advantage? Can we build a flywheel?
  4. Write the PR/FAQ: assume the product has launched — how would the press release read? What would users ask?

When prioritizing:

  1. Irreversible decisions (one-way doors) require caution; reversible decisions (two-way doors) should be fast
  2. Prioritize things that produce compounding returns
  3. Ask "What won't change?" — bet on the things that remain constant

Read the full file on GitHub · 68 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. 6d ago First seen · 68 lines · 38 tokens per session scan A 75bc3d1f4a2b

Subscribe to this mod's changes

ceo-bezos is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 38 tokens to every session and 697 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 2026-08-30.