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.
git 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/build)<a href="https://agentmods.dev/commands/app-builders-club/design-builder/build"><img src="https://agentmods.dev/badge/commands/app-builders-club/design-builder/build.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 5.1 | $0.00033 | $0.02911 |
| Opus 5 | $0.00016 | $0.01456 |
| Sonnet 5 | $0.00007 | $0.00582 |
| Haiku 4.5 | $0.00003 | $0.00291 |
Grade A, and why
build 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 6d 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/design-builder:build — generate code from spec(s)
You read one or more design specs (design/pages/<name>.md and/or design/screens/<name>.md) and emit code to the user's source tree. You do NOT design — that's /design-builder:design_page and /design-builder:design_screen. Activate the design skill.
Phase 1 — Resolve target
Parse $ARGUMENTS:
- Empty arg: list all spec files in
design/pages/anddesign/screens/. Present multi-select prompt:"Available specs:
- pages/landing
- pages/pricing
- screens/onboarding
Pick one or more (numbers, comma-separated; or
all)"
- Single name (e.g.
landing): searchdesign/pages/<name>.mdfirst, thendesign/screens/<name>.md. If both exist: preferpages/, warn user thatscreens/<name>.mdwas also found. - Explicit path (
pages/landingorscreens/onboarding): treat as the path. all: globdesign/pages/*.md+design/screens/*.md.- Glob (
pages/onboarding-*): literal glob.
If 0 spec files resolved: stop with:
"No specs found. Run
/design-builder:design_page <name>or/design-builder:design_screen <name>first."
If exactly 1 spec: single-spec mode. If N > 1: batch mode (Phase 4 batch behavior).
Phase 2 — Stack & system check (BLOCKING)
Read in order:
design/.cache/stack.json(Phase 0.5 of/setup).design/design-system.md(## Stacksection if.cache/stack.jsonis missing — fallback for migrated v2.0 projects, but log a warning that stack.json was missing).design/style-guide.md(tokens, contrast rules, motion rules, anti-patterns full prose).design/content-library.md(voice & tone, state patterns).
If stack.json says project_initialized: false:
"Project not initialized. Per
design-system.md ## Stack, run the scaffold command first (it was suggested in/setupPhase 0.4). Re-run/buildafter scaffolding."
If foundation files (design-system, style-guide, content-library) are missing → stop and point to /setup.
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.
- 6d ago First seen · 169 lines · 33 tokens per session scan A a85e4df6a199
build is a command published in the GitHub repository app-builders-club/design-builder (4 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 2,911 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
learn
Force claude-smart to extract learnings from this session now.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
check-dev
Type-check a Z specification with fuzz.