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/app-builders-club/design-builder/setupgit clone --depth 1 https://github.com/app-builders-club/design-builderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/app-builders-club/design-builder/setup)<a href="https://agentmods.dev/commands/app-builders-club/design-builder/setup"><img src="https://agentmods.dev/badge/commands/app-builders-club/design-builder/setup.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00037 | $0.05181 |
| Opus 5 | $0.00018 | $0.02590 |
| Sonnet 5 | $0.00007 | $0.01036 |
| Haiku 4.5 | $0.00004 | $0.00518 |
Grade A, and why
setup 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 3d 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 — 385 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-builder:setup — establish the design foundation
You are the entry point for a brand-new design project. Activate the design skill (skills/design/SKILL.md). You produce the artifacts in design/ that every later command (/create, /improve, /review) relies on. Until you finish, the user has no design system.
Phase 0 — Scaffold + stack detect (NEW in v2.1)
This phase runs first. No interview question is asked until 0.4 completes.
0.1 — Scaffold the design/ folder
Create the following structure (use Bash mkdir -p plus Write for the files):
design/
pages/
screens/
references/
README.md
reviews/
.cache/
.gitignore
Contents:
design/.cache/.gitignore: a single line*— excludes the entire.cache/directory from git.design/references/README.md:# Design references Drop reference materials here: - URLs and Figma links → add to `urls.md` (one per line, with optional context). - Screenshots and reference images → drop into this folder directly. Files prefixed `ref-` are auto-downloads from /setup; everything else is your manual addition. /setup, /design_page, and /design_screen all read this folder when relevant.
After scaffolding, surface this single message to the user:
"Created
design/. If you have references — drop URLs/screenshots/Figma links indesign/references/or paste them here. Ready to start? (go/ I have references)"
If the user pastes URLs in chat: append them to design/references/urls.md (create the file). If they say go: continue to 0.2 immediately.
0.2 — Detect project stack
Read these files in parallel (with Read, Glob, or Bash ls as appropriate):
package.json(root; if missing → not a JS/TS project)Package.swift,*.xcodeproj(iOS project signals)pubspec.yaml(Flutter)Cargo.toml,go.mod(signal: probably not a frontend project being designed)- root
index.html(when nopackage.jsonexists → static HTML)
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.
- 3d ago First seen · 385 lines · 37 tokens per session scan A 6bb53e0d439c
setup is a command published in the GitHub repository app-builders-club/design-builder (4 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 5,181 once invoked, about $0.0002 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.
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.