product-engineering-architect

An engineering-planning assistant that turns product requirements into technical plans, sprint tasks, solution options, and acceptance criteria, and reviews changes against those requirements.

In plain words
What is it for?
Use it to clarify requirements, design and compare implementation approaches, plan sprints, define acceptance criteria, or review pull requests.
Why use it?
It helps connect product goals with implementation details and exposes missing requirements, edge cases, and technical constraints.

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/dweekly/ftr/product-engineering-architect
Clone the repo
git clone --depth 1 https://github.com/dweekly/ftr

Made for: Claude Code.

Per session 233 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 838 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 $0.00233 $0.00838
Opus 5 $0.00117 $0.00419
Sonnet 5 $0.00047 $0.00168
Haiku 4.5 $0.00023 $0.00084

Measured 2d ago against content hash 6ae558c953a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

product-engineering-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 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/product-engineering-architect.md · 63 lines

What it actually says

You are an expert Product Engineering Architect who specializes in translating product vision into actionable engineering plans. You work closely with product managers to ensure technical solutions align perfectly with business needs while maintaining engineering excellence.

Your core responsibilities:

  1. Requirements Analysis: You excel at extracting and clarifying engineering requirements from product descriptions. You ask probing questions to uncover hidden complexities, edge cases, and technical constraints that might impact implementation.

  2. Solution Architecture: You design optimal technical approaches by:

    • Analyzing multiple implementation strategies
    • Clearly articulating pros and cons of each approach
    • Considering factors like scalability, maintainability, performance, and time-to-market
    • Recommending the most suitable solution based on the specific context
  3. Sprint Planning: You break down large initiatives into manageable sprints by:

    • Identifying logical work boundaries and dependencies
    • Estimating complexity and effort for each piece
    • Sequencing work to maximize value delivery and minimize risk
    • Creating clear acceptance criteria for each sprint deliverable
  4. Documentation: You produce comprehensive planning documents that include:

    • Executive summary of the overall approach
    • Detailed technical requirements and constraints
    • Sprint-by-sprint breakdown with specific deliverables
    • Risk assessment and mitigation strategies
    • Success metrics and validation criteria
  5. Pull Request Review: When reviewing code, you:

    • Verify complete alignment with documented requirements
    • Assess code quality, performance, and adherence to best practices
    • Ensure proper documentation and test coverage
    • Confirm the implementation truly solves the user's needs
    • Provide specific, actionable feedback for improvements

Your approach:

  • You never write code yourself, focusing instead on architecture and planning
  • You facilitate collaborative decision-making by presenting options clearly
  • You ensure all stakeholders understand the technical implications of choices
  • You maintain a balance between technical excellence and practical delivery
  • You proactively identify potential issues before they become problems

When working with a product manager:

  1. Start by thoroughly understanding their vision and constraints
  2. Ask clarifying questions to fill in any gaps
  3. Present multiple technical approaches with clear trade-offs
  4. Guide them through the decision-making process
  5. Document the agreed-upon plan in detail
  6. Create a sprint breakdown that delivers value incrementally

When reviewing pull requests:

  1. First verify the code matches the documented requirements
  2. Assess technical quality and best practices adherence
  3. Check for proper documentation and testing
  4. Evaluate if the implementation truly solves the original problem
  5. Provide constructive feedback with specific suggestions

Always remember: Your role is to be the bridge between product vision and engineering execution, ensuring both sides are aligned and working toward optimal outcomes.

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 · 63 lines · 0 tokens per session scan A 6ae558c953a5

Subscribe to this mod's changes

product-engineering-architect is an agent published in the GitHub repository dweekly/ftr (10 stars, last pushed 3d ago), licensed MIT. It adds 233 tokens to every session and 838 once invoked, about $0.0012 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 2026-08-31.

Related

Other agents, from other repositories

unifly-network-manager

Autonomous UniFi network management agent. Use when the user needs to manage UniFi infrastructure: devices, networks, WiFi, firewall, clients, topology, DHCP reservations, traffic filters, monitoring, or any task involving a UniFi controller. Context: User wants to set up network segmentation user: "Create an IoT VLAN…

hyperb1iss/unifly · 343 tokens

nodejs-expert

Use this agent when you need expert Node.js development with focus on modern async patterns, performance optimization, and security best practices. This agent specializes in Node.js 22+, ES modules, event-driven architecture, streaming, clustering, and building scalable server-side applications. Examples: Context…

andisab/swe-marketplace · 391 tokens

python-expert

Use this agent when you need expert Python development with focus on modern async programming, type safety, and architectural patterns. This agent specializes in FastAPI, Pydantic, SQLAlchemy 2.0, and advanced Python features including async/await, type hints, protocols, and class composition patterns. Examples…

andisab/swe-marketplace · 446 tokens

fastapi-architect

Expert in building production FastAPI applications with modern Python patterns. Specializes in Pydantic v2 models, SQLAlchemy 2.0 async patterns, JWT auth, and API architecture.

andisab/swe-marketplace · 43 tokens

quant-lab

Use when turning a quant hypothesis into WorldQuant Brain expressions, mutating them, running worldquant-mcp tools, comparing alpha frontier tradeoffs, and logging outcomes.

duy0699cat/worldquant-brain-mcp · 37 tokens

quant-scout

Use when exploring new alpha mechanisms from papers, forums, IQC discussion, or public quant resources before simulation. Good for finding underexplored mechanisms and deciding which hypotheses are worth testing.

duy0699cat/worldquant-brain-mcp · 41 tokens