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/sample-datagit 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 | $0.02006 |
| Opus 5 | $0.00000 | $0.01003 |
| Sonnet 5 | $0.00000 | $0.00401 |
| Haiku 4.5 | $0.00000 | $0.00201 |
Grade A, and why
sample-data 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 yesterday.
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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sample Data
You are helping the user create or update realistic sample data for a section of their product. This data will be used to populate screen designs. You will also generate TypeScript types based on the data structure.
Step 1: Check Prerequisites
First, identify the target section and verify that spec.md exists for it.
Read /product/product-roadmap.md to get the list of available sections.
If there's only one section, auto-select it. If there are multiple sections, use the AskUserQuestion tool to ask which section the user wants to generate data for.
Then check if product/sections/[section-id]/spec.md exists. If it doesn't:
"I don't see a specification for [Section Title] yet. Please run /shape-section first to define the section's requirements, then come back to generate sample data."
Stop here if the spec doesn't exist.
Step 2: Check for Existing Sample Data
Check if product/sections/[section-id]/data.json already exists.
If sample data already exists:
Read the existing data.json and types.ts files, then ask the user:
"Sample data already exists for [Section Title]. What would you like to change about the existing data shape or sample data?"
Wait for the user's response describing what they want changed. Once you receive their notes, immediately proceed to update data.json and types.ts based on their requested changes — do not present a draft for approval.
After updating, inform the user:
"I've updated the sample data and types for [Section Title] based on your feedback. Review the changes and let me know if you'd like further adjustments, or run /design-screen when you're ready."
Stop here — the remaining steps below are for generating new data from scratch.
If no sample data exists: Continue to Step 3.
Step 3: Check for Global Data Shape
Check if /product/data-shape/data-shape.md exists.
If it exists:
- Read the file to understand the global entity definitions
- Entity names in your sample data should match the global data shape
- Use the descriptions and relationships as a guide
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.
- yesterday First seen · 234 lines · 0 tokens per session scan A 2d7592b5f783
sample-data is a command published in the GitHub repository buildermethods/design-os (1,845 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,006 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
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.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.