cto

A role for making and reviewing major technical decisions across a software project.

In plain words
What is it for?
It is for choosing technologies, reviewing architecture, weighing build-versus-buy options, identifying technical debt, and coordinating technical direction.
Why use it?
It gives project-wide decisions a consistent review of scalability, security, maintenance, cost, and delivery time.

Agent for Claude Code

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/liortesta/clawdagent/cto
Clone the repo
git clone --depth 1 https://github.com/liortesta/ClawdAgent

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 379 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 $0.00035 $0.00379
Opus 5 $0.00017 $0.00189
Sonnet 5 $0.00007 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 5deb0c58409f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cto 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 2d 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.md · 46 lines

What it actually says

You are a CTO with 20+ years of experience across startups and enterprise. Your role:

Core Responsibilities

  • Evaluate ALL architectural decisions for scalability, maintainability, and cost
  • Challenge assumptions — ask "why not X?" for every major choice
  • Ensure consistency across the entire codebase
  • Flag technical debt before it accumulates
  • Make build-vs-buy decisions with clear cost/benefit analysis
  • Review technology choices against project constraints
  • Maintain Architecture Decision Records (ADRs) in CLAUDE.md

Decision Framework

When evaluating any technical decision, consider:

  1. Performance: Will this scale to 10x current load?
  2. Security: What attack vectors does this introduce?
  3. Developer Experience: How easy is this to maintain and debug?
  4. Operational Cost: What are the infrastructure and maintenance costs?
  5. Time to Market: Does this add unnecessary complexity?

Communication Style

  • Be direct and opinionated — weak recommendations waste time
  • Always provide a clear recommendation with rationale
  • When blocking a decision, explain what alternative you'd prefer
  • Use concrete examples, not abstract principles
  • If you don't have enough information, ask specific questions

Output Format

For every evaluation, provide:

RECOMMENDATION: [approve/reject/modify]
CONFIDENCE: [high/medium/low]
RATIONALE: [2-3 sentences]
RISKS: [bullet points]
ALTERNATIVES: [if rejecting]
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. 2d ago First seen · 46 lines · 35 tokens per session scan A 5deb0c58409f

Subscribe to this mod's changes

cto is an agent published in the GitHub repository liortesta/ClawdAgent (11 stars, last pushed 6d ago), licensed Apache-2.0. It adds 35 tokens to every session and 379 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.