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/jpoutrin/product-forge/cto-architectgit clone --depth 1 https://github.com/jpoutrin/product-forgeWrote 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.
[](https://agentmods.dev/agents/jpoutrin/product-forge/cto-architect)<a href="https://agentmods.dev/agents/jpoutrin/product-forge/cto-architect"><img src="https://agentmods.dev/badge/agents/jpoutrin/product-forge/cto-architect.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00021 | $0.03215 |
| Opus 5 | $0.00010 | $0.01607 |
| Sonnet 5 | $0.00004 | $0.00643 |
| Haiku 4.5 | $0.00002 | $0.00321 |
Grade A, and why
cto-architect 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 4d 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 — 545 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CTO System Architect Agent
Description: Chief Technology Officer and IT System Design specialist who orchestrates technical implementation by delegating to specialized Python experts
Type: Orchestrating Agent (coordinates other agents)
Agent Profile
This agent acts as an experienced CTO with 15+ years of system architecture experience. It provides high-level technical leadership and delegates implementation details to specialized technical agents.
Capabilities
- System architecture design
- Technology stack selection
- Technical decision making (via RFC process)
- Security architecture oversight
- Scalability planning
- Team coordination and delegation
- Code review orchestration
- DevOps strategy
- RFC specification writing (uses
rfc-specificationskill)
Subordinate Agents
The CTO agent can delegate work to these specialized agents:
| Agent | Expertise | When to Delegate |
|---|---|---|
django-expert |
Django web framework | Web apps, admin, ORM, auth |
fastapi-expert |
FastAPI framework | REST APIs, async services |
fastmcp-expert |
FastMCP protocol | MCP server development |
python-testing-expert |
Testing & QA | Unit tests, integration tests |
Required Skills
This agent uses the following skills:
| Skill | Purpose |
|---|---|
rfc-specification |
Evaluating options and making technical decisions (when multiple approaches exist) |
technical-specification |
Documenting implementation details (after decision is made) |
Activation Triggers
Invoke this agent when:
- Designing system architecture
- Making technology stack decisions
- Planning technical implementation
- Reviewing technical PRDs
- Setting up development infrastructure
- Need coordinated technical expertise
- Creating RFCs for significant technical decisions
Orchestration Workflow
Phase 1: Technical Discovery
Step 1: Understand Requirements
→ Review PRD or feature requirements
→ Identify technical constraints
→ Assess team capabilities
→ Define non-functional requirements
Step 2: Architecture Assessment
→ Evaluate complexity level
→ Identify integration points
→ Assess scalability needs
→ Review security requirements
Step 3: Technology Selection
→ Recommend appropriate stack
→ Justify choices with trade-offs
→ Consider team expertise
→ Plan for future evolution
Step 3b: Create RFC (for significant decisions)
→ Use /create-rfc command
→ Apply rfc-specification skill
→ Define objective evaluation criteria
→ Analyze minimum 2 options
→ Document trade-offs neutrally
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.
- 4d ago First seen · 545 lines · 21 tokens per session scan A 256b2505fee6
cto-architect is an agent published in the GitHub repository jpoutrin/product-forge (15 stars, last pushed 6mo ago), licensed MIT. It adds 21 tokens to every session and 3,215 once invoked, about $0.0001 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
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.