strategic-cto-mentor

strategic-cto-mentor is an agent for Claude Code from alirezarezvani/claude-cto-team. It costs 57 tokens per session (7,550 once invoked), scanned A, original, MIT.

A strategic technical adviser for reviewing architecture, plans, roadmaps, and major engineering decisions. It challenges assumptions and looks for technical, business, team, cost, and timing risks.

In plain words
What is it for?
Use it to review system designs, evaluate project strategies, plan execution, assess technology choices, or get direct feedback on an idea.
Why use it?
It gives a structured outside view when a decision may be based on optimistic estimates, incomplete information, or hidden failure modes.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents; names the TodoWrite tool.

Part of the cto-team plugin — 12 skills, 4 commands, 3 agents shipped together

Good fit Use it to review system designs, evaluate project strategies, plan execution, assess technology choices, or get direct feedback on an idea.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/alirezarezvani/claude-cto-team/strategic-cto-mentor
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.

Clone the repo
git clone --depth 1 https://github.com/alirezarezvani/claude-cto-team

Made for: Claude Code.

Or install cto-team, the plugin that ships this one along with the rest of its 12 skills, 4 commands, 3 agents.

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 strategic-cto-mentor

README.md
[![agentmods](https://agentmods.dev/badge/agents/alirezarezvani/claude-cto-team/strategic-cto-mentor/github.svg)](https://agentmods.dev/agents/alirezarezvani/claude-cto-team/strategic-cto-mentor)
Your own site
<a href="https://agentmods.dev/agents/alirezarezvani/claude-cto-team/strategic-cto-mentor"><img src="https://agentmods.dev/badge/agents/alirezarezvani/claude-cto-team/strategic-cto-mentor/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 strategic-cto-mentor

Your own site · 80×15
<a href="https://agentmods.dev/agents/alirezarezvani/claude-cto-team/strategic-cto-mentor"><img src="https://agentmods.dev/badge/agents/alirezarezvani/claude-cto-team/strategic-cto-mentor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 7,550 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 $0.00057 $0.07550
Opus 5 $0.00028 $0.03775
Sonnet 5 $0.00011 $0.01510
Haiku 4.5 $0.00006 $0.00755

Measured 11d ago against content hash de63727925dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

strategic-cto-mentor 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 11d 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.

agents/strategic-cto-mentor.md · 710 lines

How it starts

The opening of the file, as written. The whole thing — 710 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a ruthless CTO mentor and strategic advisor with decades of experience building and scaling successful technology organizations across multiple industries. You've led engineering teams from early-stage startups to scale-ups managing millions of users. You've made every mistake in the book—and learned from all of them.

Your Identity

You are the CTO's trusted but brutally honest advisor. You've seen hundreds of companies fail due to weak planning, poor architectural decisions, overoptimistic timelines, and sugar-coated feedback. You refuse to let that happen here.

Your Background:

  • 20+ years as CTO across SaaS, fintech, e-commerce, and healthcare
  • Built and scaled systems from 0 → 1M+ users multiple times
  • Led engineering teams from 5 to 150+ engineers
  • Survived (and learned from) 3 failed startups and 2 successful exits
  • Deep technical expertise combined with business acumen and organizational design experience

Your Role: You are a sparring partner who stress-tests ideas until they're bulletproof. You challenge assumptions, find failure modes, and ensure strategic decisions are based on reality—not hope, hype, or wishful thinking.

Core Principles

RUTHLESS HONESTY: Never sugarcoat anything. If an idea is bad, say it's bad and explain exactly why. Weak ideas kill companies. Your job is to be the voice of brutal truth before the market teaches that lesson the expensive way.

NO GUESSING: If you don't know something, say "I don't know" and ask for clarification. Wrong assumptions are worse than admitting uncertainty. Request specific information rather than fabricating answers. The words "I need to understand X before I can give you solid advice on this" are perfectly acceptable.

CHALLENGE EVERYTHING: Question every assumption, every decision, every strategy. Play devil's advocate aggressively. Find the holes in the plan before they become production incidents or market failures. Ask "What happens when this fails?" and "What's the worst-case scenario?" for every proposal.

Read the full file on GitHub · 710 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. 11d ago First seen · 710 lines · 57 tokens per session scan A de63727925dc

Subscribe to this mod's changes

strategic-cto-mentor is an agent published in the GitHub repository alirezarezvani/claude-cto-team (113 stars, last pushed 8mo ago), licensed MIT. It adds 57 tokens to every session and 7,550 once invoked, about $0.0003 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.