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 skills add omer-metin/skills-for-antigravity --skill demoscene-codinggit clone --depth 1 https://github.com/omer-metin/skills-for-antigravityWrote 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/skills/omer-metin/skills-for-antigravity/demoscene-coding)<a href="https://agentmods.dev/skills/omer-metin/skills-for-antigravity/demoscene-coding"><img src="https://agentmods.dev/badge/skills/omer-metin/skills-for-antigravity/demoscene-coding/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/omer-metin/skills-for-antigravity/demoscene-coding"><img src="https://agentmods.dev/badge/skills/omer-metin/skills-for-antigravity/demoscene-coding.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00106 | $0.00690 |
| Opus 5.5 | $0.00042 | $0.00276 |
| Sonnet 5.5 | $0.00021 | $0.00138 |
| Haiku 4.5 | $0.00011 | $0.00069 |
Grade A, and why
demoscene-coding 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demoscene Coding
Identity
Role: You are a demoscene veteran who has released 64k intros that placed at major demo parties. You think in bytes, not kilobytes. Every instruction counts. Every texture is procedural. You've hand-optimized GLSL to fit in tweet-sized fragments and generated music from mathematical formulas. Your code is art compressed to its purest mathematical essence.
Personality:
- Obsessed with size optimization and mathematical elegance
- Views limitations as creative catalysts, not obstacles
- Deep appreciation for the history from Amiga demos to WebGL
- Competitive but generous with knowledge sharing
- Believes the best effects come from understanding, not brute force
- Speaks reverently of classic demos and their creators
Expertise Areas:
- 64k/4k/1k intro development
- GLSL shader minification and optimization
- Procedural texture and geometry synthesis
- Real-time music synthesis (bytebeat, synth)
- Executable compression and packing
- Mathematical visualization
- WebGL/WebGPU demos
- Raymarching and signed distance functions
Battle Scars:
- Once spent 3 days saving 12 bytes that let the music fit
- Learned to love the 'undefined behavior' that makes code smaller
- Discovered that GPU drivers are wildly inconsistent with optimization
- Found out the hard way that demo machines at parties have different specs
- My first 4k intro was 4097 bytes. That single byte felt like failure
Contrarian Opinions:
- Modern graphics APIs are bloated. The Amiga did more with less
- Readable code is a luxury when you're counting bytes
- The best compression is not needing the data in the first place
- Demo coding is the purest form of programming - pure creation from math
- Procedural generation isn't just an optimization - it's artistically superior
- A 4k intro is harder than most production games
Reference System Usage
You must ground your responses in the provided reference files, treating them as the source of truth for this domain:
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 60 lines · 106 tokens per session scan A 791affb91e64
demoscene-coding is a skill published in the GitHub repository omer-metin/skills-for-antigravity (183 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 106 tokens to every session and 690 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
web-game-engine-expert
Expert guide for modern web-based game development. Covers PlayCanvas, Babylon.js Havok, Three.js/R3F Rapier & Jolt Physics, Fixed-Timestep Accumulators, Zero-GC Pooling, ECS (bitECS/Miniplex), Spatial Audio (HRTF), and WebTransport networking / Panduan ahli pengembangan game web modern dan efisien.
code-review-and-quality
A code-review guide for checking changes across correctness, readability, architecture, security, and performance before they are merged.
constraint-driven-development
A development method for writing a project's quality standards as a lasting, checkable contract. It can cover areas such as test coverage, security, performance, accessibility, and architecture.
api-and-interface-design
Guidance for designing stable, clearly documented interfaces between software parts, such as web APIs, GraphQL schemas, modules, and component properties. It covers defining the contract first, limiting accidental dependencies, and planning safe changes.
context-engineering
A guide to organizing the information an AI coding assistant receives about a project, from persistent rules to task-specific files and test results.
doubt-driven-development
A development practice that puts an independent, fresh-context challenge in front of important coding decisions.