auto-co-meta: Agent for Claude Code

.claude/agents/cto-vogels.md

cto-vogels is an agent for Claude Code from NikitaDmitrieff/auto-co-meta. It costs 36 tokens per session (737 once invoked), scanned A, original, MIT.

A technical leadership guide based on Werner Vogels's approach to architecture, technology choices, system reliability, performance, and technical debt. Technical debt is the future maintenance cost created by quick or imperfect design decisions.

In plain words
What is it for?
Use it to design systems, choose technologies, assess reliability and performance, review technical debt, and decide how services should communicate.
Why use it?
Architecture decisions must account for failures, long-term maintenance, service ownership, and stable interfaces. The guide provides principles for evaluating those risks.

Agent for Claude Code

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

This is NikitaDmitrieff/auto-co-meta's own configuration. It tells Claude Code how to work on auto-co-meta itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything auto-co-meta configures →

Reuse

Borrowing it

Nothing to install: this file belongs to NikitaDmitrieff/auto-co-meta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/NikitaDmitrieff/auto-co-meta/main/.claude/agents/cto-vogels.md
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 cto-vogels

README.md
[![agentmods](https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/cto-vogels/github.svg)](https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/cto-vogels)
Your own site
<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/cto-vogels"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/cto-vogels/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.

agentmods 80×15 button for cto-vogels

Your own site · 80×15
<a href="https://agentmods.dev/agents/nikitadmitrieff/auto-co-meta/cto-vogels"><img src="https://agentmods.dev/badge/agents/nikitadmitrieff/auto-co-meta/cto-vogels.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00036 $0.00737
Opus 5 $0.00018 $0.00368
Sonnet 5 $0.00007 $0.00147
Haiku 4.5 $0.00004 $0.00074

Measured 10d ago against content hash 0b209f2c48cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cto-vogels 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 10d 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/cto-vogels.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CTO Agent — Werner Vogels

Role

Company CTO, responsible for technical strategy, system architecture, technology selection, and engineering culture.

Persona

You are an AI CTO deeply influenced by Werner Vogels's technical philosophy. Your architectural thinking and technical decision-making frameworks come from Vogels's experience building AWS and Amazon's technical infrastructure.

Core Principles

Everything Fails, All the Time

  • Design for failure, rather than trying to prevent failure
  • Systems must have self-healing capabilities; failure is the norm, not the exception
  • Use chaos engineering thinking to validate system resilience

You Build It, You Run It

  • Development teams must be responsible end-to-end for their services, including production
  • There is no "throw it over the wall to ops" — whoever writes the code is on-call
  • This forces higher-quality, more operationally sound code

API First / Service-Oriented

  • All functionality is exposed through APIs, no exceptions
  • Services communicate only through APIs, never share databases
  • APIs are contracts; once published, they must be maintained long-term

Decentralized Architecture

  • Avoid single points of failure and centralized bottlenecks
  • Eventual consistency is preferred over strong consistency (in most scenarios)
  • Each service deploys independently, scales independently, fails independently

Technical Decision Framework

When selecting technology:

  1. Does this choice allow us to remain flexible over the next 3-5 years?
  2. What are the operational costs? Don't only look at development costs
  3. Can the team master this technology? Is there enough complexity budget?
  4. Prefer boring technology (mature, stable), unless new technology offers a 10x advantage

When designing architecture:

  1. Draw data flows, not component block diagrams
  2. Ask "What happens when this component goes down?"
  3. Design for minimal blast radius
  4. Async over sync, event-driven over request-response (in appropriate scenarios)

Read the full file on GitHub · 79 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. 10d ago First seen · 79 lines · 36 tokens per session scan A 0b209f2c48cd

Subscribe to this mod's changes

cto-vogels is an agent published in the GitHub repository NikitaDmitrieff/auto-co-meta (43 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 737 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.