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/data-shapegit 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 | $0.00839 |
| Opus 5 | $0.00000 | $0.00419 |
| Sonnet 5 | $0.00000 | $0.00168 |
| Haiku 4.5 | $0.00000 | $0.00084 |
Grade A, and why
data-shape 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Shape
You are helping the user create or update the general shape of their product's data — the core entities ("nouns") and how they relate to each other. This creates a shared vocabulary that ensures consistency across sections when generating sample data and screen designs. This is not the final data model — it's a starting point that the implementation agent will extend and refine.
Step 1: Check Current State
First, check if /product/data-shape/data-shape.md exists.
If Data Shape Already Exists (Updating)
Read:
/product/data-shape/data-shape.md/product/product-overview.md(if it exists, for context)/product/product-roadmap.md(if it exists, for context)
Present the current state and ask what to change:
"Your data shape currently defines these entities:
- [Entity1] — [Description]
- [Entity2] — [Description]
Relationships:
- [Relationship 1]
- [Relationship 2]
What would you like to change about the entities or relationships?"
Wait for the user's response describing what they want changed. Once you receive their notes, immediately proceed to update product/data-shape/data-shape.md based on their requested changes — do not present a draft for approval.
After updating, inform the user:
"I've updated the data shape based on your feedback. Review the changes and let me know if you'd like further adjustments."
Stop here — the remaining steps below are for generating a new data shape from scratch.
If No Data Shape Exists (Creating New)
Check Prerequisites
Read:
/product/product-overview.mdto understand what the product does/product/product-roadmap.mdto understand the planned sections
If either file is missing, let the user know:
"Before defining your data shape, you'll need to establish your product vision. Please run /product-vision first."
Stop here if prerequisites are missing.
Analyze and Generate
Review the product overview and roadmap, then immediately proceed to create the data shape file — do not present a draft for approval.
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 · 113 lines · 0 tokens per session scan A ca87ad25a676
data-shape is a command published in the GitHub repository buildermethods/design-os (1,845 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 839 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.