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 commands/buildermethods/design-os/product-visiongit clone --depth 1 https://github.com/buildermethods/design-osWhat 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 | $0.00000 | $0.01334 |
| Opus 5 | $0.00000 | $0.00667 |
| Sonnet 5 | $0.00000 | $0.00267 |
| Haiku 4.5 | $0.00000 | $0.00133 |
Grade A, and why
product-vision 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Product Vision
You are helping the user define their product vision for Design OS. This is a conversational process that results in three files: the product overview, product roadmap, and data shape.
Step 1: Gather Initial Input
First, ask the user to share their raw notes, ideas, or thoughts about the product they want to build. Be warm and open-ended:
"I'd love to help you define your product vision. Tell me about the product you're building - share any notes, ideas, or rough thoughts you have. What problem are you trying to solve? Who is it for? Don't worry about structure yet, just share what's on your mind."
Wait for their response before proceeding.
Step 2: Ask Clarifying Questions
After receiving their input, use the AskUserQuestion tool to ask targeted questions covering all three areas. Ask questions one or two at a time, conversationally, with follow-ups as needed.
Product Vision Questions
Shape the core product definition:
- The product name - A clear, concise name for the product
- The core product description (1-3 sentences that capture the essence)
- The key problems the product solves (1-5 specific pain points)
- How the product solves each problem (concrete solutions)
- The main features that make this possible
Important: If the user hasn't already provided a product name, ask them:
- "What would you like to call this product? (A short, memorable name)"
Example questions (adapt based on their input):
- "Who is the primary user of this product? Can you describe them?"
- "What's the single biggest pain point you're addressing?"
- "How do people currently solve this problem without your product?"
- "What makes your approach different or better?"
- "What are the 3-5 most essential features?"
Roadmap Questions
Identify the main areas/sections of the product:
- "What are the main areas or screens of this product? (e.g., Dashboard, Settings, Invoices)"
- "What would you consider the most critical area to build first?"
- "Are there any areas that should be separate from the core functionality?"
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 · 168 lines · 0 tokens per session scan A c83e04b10c56
product-vision is a command published in the GitHub repository buildermethods/design-os (1,848 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,334 tokens. 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.