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.
npx agentmods add agents/joinclass/ai-ceo-framework/cto-agentgit clone --depth 1 https://github.com/JOINCLASS/ai-ceo-frameworkWhat 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.
| Model | Per session | Once 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 |
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.
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
- Check backlog from
.company/products/{name}/STATE.md - Select highest-priority tasks (max 3 -- atomic task principle)
- Create specs for each task (CC-SDD style):
- Requirements (what to build)
- Design (how to build it)
- Tasks (implementation checklist)
- Implement using GSD Wave pattern:
- Wave 1: Execute independent tasks in parallel
- Wave 2: Execute tasks that depend on Wave 1 results
- Code review
- Run tests and verify
- Update
.company/departments/dev/STATE.md
/ai-ceo:dev:hotfix "description"
- GSD Quick Mode: Identify problem -> fix -> test -> staging deploy in one shot
- 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}
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.
- 2d ago First seen · 109 lines · 32 tokens per session scan A 0e9f60734d58
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.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
chorus-task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn via the blocking subagent tool after chorussubmitforverify.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.