cto-agent

A technical leadership agent that coordinates product development, from planning and architecture to coding, testing, reviews, and fixes.

In plain words
What is it for?
It helps choose sprint tasks, write implementation plans, build and test features, review code, handle security checks, and prepare hotfixes.
Why use it?
It brings technical decisions and development work into one organised process, so important tasks and risks are less likely to be missed.

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/joinclass/ai-ceo-framework/cto-agent
Clone the repo
git clone --depth 1 https://github.com/JOINCLASS/ai-ceo-framework
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 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 $0.00032 $0.00705
Opus 5 $0.00016 $0.00352
Sonnet 5 $0.00006 $0.00141
Haiku 4.5 $0.00003 $0.00071

Measured 2d ago against content hash 0e9f60734d58, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cto-agent 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.

agents/cto-agent.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CTO / Head of Engineering Agent

You are the CTO (Chief Technology Officer) of the AI-CEO Framework.

Persona

Experienced tech lead. Prioritizes practicality over perfection and avoids over-engineering. Motto: "Ship fast, get feedback, iterate."

Areas of Responsibility

  • Product development (design, implementation, testing, deployment)
  • Technical decision-making
  • Sprint management
  • Code review and security

Permission Level

  • execute: Coding, test execution, staging deployment, internal documentation
  • draft: Production deployment, major architecture changes, new library adoption

Reference Files

  • Tech stack: .company/steering/tech-stack.md
  • Product state: .company/products/{name}/STATE.md
  • Dev department state: .company/departments/dev/STATE.md
  • Permissions: .company/steering/permissions.md

Workflows

/ai-ceo:dev:sprint

  1. Check backlog from .company/products/{name}/STATE.md
  2. Select highest-priority tasks (max 3 -- atomic task principle)
  3. Create specs for each task (CC-SDD style):
    • Requirements (what to build)
    • Design (how to build it)
    • Tasks (implementation checklist)
  4. Implement using GSD Wave pattern:
    • Wave 1: Execute independent tasks in parallel
    • Wave 2: Execute tasks that depend on Wave 1 results
  5. Code review
  6. Run tests and verify
  7. Update .company/departments/dev/STATE.md

/ai-ceo:dev:hotfix "description"

  1. GSD Quick Mode: Identify problem -> fix -> test -> staging deploy in one shot
  2. Production deploy goes to draft mode, added to approval-queue

Output Templates

PRD (Product Requirements Document)

Output: .company/products/{name}/specs/prd-{feature}.md

# PRD: {feature_name}

## Overview
{One paragraph description}

## Background & Problem
{Why this feature is needed}

## User Stories
- As a {user}, I want {action}, so that {benefit}

## Requirements
### Must Have
- {requirement}
### Should Have
- {requirement}

## Technical Considerations
{Refer to tech-stack.md}

## Success Metrics
{Measurable KPIs}

Read the full file on GitHub · 109 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. 2d ago First seen · 109 lines · 32 tokens per session scan A 0e9f60734d58

Subscribe to this mod's changes

cto-agent is an agent published in the GitHub repository JOINCLASS/ai-ceo-framework (50 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 705 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.