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/design-screengit 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 | $0.02443 |
| Opus 5 | $0.00000 | $0.01222 |
| Sonnet 5 | $0.00000 | $0.00489 |
| Haiku 4.5 | $0.00000 | $0.00244 |
Grade A, and why
design-screen 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Screen
You are helping the user create a screen design for a section of their product. The screen design will be a props-based React component that can be exported and integrated into any React codebase.
Step 1: Check Prerequisites
First, identify the target section and verify that spec.md, data.json, and types.ts all exist.
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 create a screen design for.
Then verify all required files exist:
product/sections/[section-id]/spec.mdproduct/sections/[section-id]/data.jsonproduct/sections/[section-id]/types.ts
If spec.md doesn't exist:
"I don't see a specification for [Section Title] yet. Please run /shape-section first to define the section's requirements."
If data.json or types.ts don't exist:
"I don't see sample data for [Section Title] yet. Please run /sample-data first to create sample data and types for the screen designs."
Stop here if any file is missing.
Step 2: Check for Design System and Shell
Check for optional enhancements:
Design Tokens:
- Check if
/product/design-system/colors.jsonexists - Check if
/product/design-system/typography.jsonexists
If design tokens exist, read them and use them for styling. If they don't exist, show a warning:
"Note: Design tokens haven't been defined yet. I'll use default styling, but for consistent branding, consider running /design-tokens first."
Shell:
- Check if
src/shell/components/AppShell.tsxexists
If shell exists, the screen design will render inside the shell in Design OS. If not, show a warning:
"Note: An application shell hasn't been designed yet. The screen design will render standalone. Consider running /design-shell first to see section screen designs in the full app context."
Step 3: Analyze Requirements
Read and analyze all three files:
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 · 310 lines · 0 tokens per session scan A 5cf8a3270997
design-screen is a command published in the GitHub repository buildermethods/design-os (1,848 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,443 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.