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/overdrive)<a href="https://agentmods.dev/commands/obiwancenobi/klamben/overdrive"><img src="https://agentmods.dev/badge/commands/obiwancenobi/klamben/overdrive.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 | $0.00028 | $0.00512 |
| Opus 5 | $0.00014 | $0.00256 |
| Sonnet 5 | $0.00006 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
overdrive 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.
What it actually says
/overdrive
Go beyond standard widgets. For moments that need to feel exceptional — onboarding, celebrations, premium features, hero moments.
When to use
- User wants a "wow" moment
- Onboarding or first-run experience
- Achievement/celebration screens
- Premium feature showcase
- User explicitly asks for advanced effects
Process
- Check design context: If
.klamben.mdexists in the project root, read it first. Overdrive effects should match the brand tone. - Identify the moment — What specific interaction or screen deserves the extraordinary treatment? (Not everything — pick one.)
- Choose the technique:
- Custom painting (
CustomPainter) — animated backgrounds, progress rings, custom charts, wave effects - Shader effects (
FragmentProgram) — blur, glow, gradient mesh, frosted glass - Particle systems — celebration confetti, floating elements, ambient particles
- Complex gestures — drag-to-dismiss with physics, pinch-zoom with momentum, swipe cards
- Parallax — layered scroll with depth
- Morphing —
HerowithflightShuttleBuilder, shape morphing viaTweenAnimationBuilder - Staggered animations — sequenced entry of list items, cascading reveals
- Custom painting (
- Implement with performance in mind:
RepaintBoundaryaround the effectAnimatedBuildernotsetState- Dispose all controllers
- Respect
MediaQuery.disableAnimations - Test on low-end devices (profile mode)
- Keep it contained — the effect should enhance one moment, not spread across the whole screen
- Add fallback for reduced-motion users (static version of the effect)
Do NOT
- Apply overdrive effects to routine UI (buttons, lists, forms)
- Skip performance considerations
- Ignore reduced-motion accessibility
- Use effects that distract from the primary action
- Add particle effects to business/enterprise apps unless explicitly asked
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 · 60 lines · 28 tokens per session scan A af954bb88613
overdrive is a command published in the GitHub repository obiwancenobi/klamben (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 512 once invoked, about $0.0001 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
generate-web-diagram
Generate a beautiful standalone HTML diagram and open it in the browser.
generate-web-diagram
Generate a beautiful standalone HTML diagram and open it in the browser.
create
Generate a brandable, GitHub-Pages-ready Forward Deploy Engineering consulting website into docs/ — interviews you for brand, pricing and contact, saves fde-site.config.yaml, and renders from a market preset.
optimize-images
Optimize all images in the project for web performance. Convert images to modern formats (WebP, AVIF) with fallbacks. Replace img tags with Next.js Image component for automatic optimization. Add proper width/height attributes to prevent layout shift. Implement lazy loading for below-fold images. Compress existing…
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.