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/obiwancenobi/klambenWrote 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/obiwancenobi/klamben/craft)<a href="https://agentmods.dev/commands/obiwancenobi/klamben/craft"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/craft.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 | $0.00031 | $0.00644 |
| Opus 5 | $0.00015 | $0.00322 |
| Sonnet 5 | $0.00006 | $0.00129 |
| Haiku 4.5 | $0.00003 | $0.00064 |
Grade A, and why
craft 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 7d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/craft
Design-first screen creation. Shape the concept, then build the widgets. Prevents the "just start coding" trap that produces generic-looking screens.
When to use
- Building a new screen from scratch
- User says "build me a..." / "create a..." / "make a screen for..."
- Whenever the output is a full screen or major feature, not a tweak
Process
- Check design context: If
.klamben.mdexists in the project root, read it first. Apply the project's brand, platform targets, accessibility tier, and existing patterns to your work below.
Phase 1: Shape (no code yet)
- Clarify purpose — What does this screen do? What's the one thing the user accomplishes here? If unclear, ask.
- Identify content hierarchy — What's the most important element?
What's secondary? What's optional? Sketch a mental wireframe:
- Primary action (FAB, bottom CTA, inline button)
- Key content (hero, list, form, card)
- Supporting info (subtitle, metadata, timestamp)
- Navigation (back, tabs, drawer)
- Choose layout pattern — Based on content:
- List →
ListView.builder+ item widgets - Detail → scroll + hero + sections
- Form →
SingleChildScrollView+Form - Dashboard → grid or card stack
- Empty/loading/error states for each
- List →
- Present the shape to the user as a text wireframe:
Ask: "Does this layout match what you need?"[AppBar: "Screen Title"] [Hero image / avatar] [Title — headlineMedium] [Subtitle — bodyMedium, onSurfaceVariant] [--- Divider ---] [List of items] [FAB: "Add item"]
Phase 2: Build
- Write the widget using theme tokens, not hardcoded values. Apply all klamben rules from the start — no cleanup pass needed.
- Add states — loading, error, empty (using
/empty-statepatterns) - Add platform adaptation if
.klamben.mdsays cross-platform - Present the result — show the code, explain key design decisions
Phase 3: Iterate
- Ask: "What would you change?" Iterate on feedback.
- When satisfied, suggest: "Run
/auditto verify, then/polishfor final cleanup."
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.
- 7d ago First seen · 75 lines · 31 tokens per session scan A b50238320442
craft is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 644 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
ux-recommend
The v2 flagship. Runs the 5-parallel-search Python engine across 11 data manifests (75+ styles, 170+ palettes, 65+ type pairs, 120+ components, 170+ industries, 110+ UX laws, 50+ motion presets, 120+ anti-patterns, 92 brand specs) and returns a complete recommended design system for your project — with always-on…
color-specialist
Use when colour is failing. Contrast below AA, a palette with no system behind it, dark mode that is only inverted light mode, or semantic colours that carry no meaning.
responsive-design-specialist
Use when a layout breaks between sizes. Arbitrary breakpoints, type that does not scale, images that blow out the grid, or a desktop design retrofitted onto mobile.
revisar-ui
Auditoria visual retroativa de 6 pilares do código frontend implementado.
extract
Pull repeated patterns into reusable components and design tokens.
improve-ui-ux
Audit and improve an existing interface through one evidence-backed, design-system-aware implementation and browser-verification pass.