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 J-StaR-Films-Studios/VibeCode-Protocol-Suite --skill creative-web-developmentgit clone --depth 1 https://github.com/J-StaR-Films-Studios/VibeCode-Protocol-SuiteWrote 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/j-star-films-studios/vibecode-protocol-suite/creative-web-development)<a href="https://agentmods.dev/skills/j-star-films-studios/vibecode-protocol-suite/creative-web-development"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/creative-web-development/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/j-star-films-studios/vibecode-protocol-suite/creative-web-development"><img src="https://agentmods.dev/badge/skills/j-star-films-studios/vibecode-protocol-suite/creative-web-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.02658 |
| Opus 5 | $0.00021 | $0.01329 |
| Sonnet 5 | $0.00008 | $0.00532 |
| Haiku 4.5 | $0.00004 | $0.00266 |
Grade A, and why
creative-web-development 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 5d 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creative Web Development
Create experiences with a clear visual idea and carefully selected technology that makes that idea possible.
Treat creative direction and creative engineering as separate decisions. Establish what the experience means, how it should feel, and what visitors need before selecting implementation techniques.
Route the Request
Classify the request before producing a plan or changing code.
| Request state | Route |
|---|---|
| Sparse brief; the user wants ideas, a direction, or a plan | Read references/creative-direction.md, then references/concept-evaluation.md. |
| Evidence-rich history, case study, launch story, or project retrospective | Read references/story-engineering.md, then references/concept-evaluation.md. |
| The user already supplied a governing concept or detailed art direction | Preserve it and continue at Experience Architecture. |
| The user asks for one technique, implementation, or bug fix | Route directly to the relevant technical reference. Do not redesign the experience. |
| The user asks for a creative audit | Read references/concept-evaluation.md; add references/performance-and-profiling.md only when implementation exists. |
Reference Loading Contract
The router selects references; selection makes reading them mandatory. Do not substitute prior knowledge, remembered APIs, summaries, implementation examples, or the main skill for the current reference files.
- Build a Reference Manifest listing every capability the task requires and the reference that governs it.
- Read every selected reference completely before making detailed decisions or writing code.
- Record a compact Reference Receipt with the file path and at least one non-obvious constraint from that file that changes the plan or implementation.
- If a new capability enters scope, pause that part of the work, add its reference to the manifest, and read it before continuing.
- Read references/performance-and-profiling.md whenever the solution includes an animation loop, smooth-scroll orchestration, Canvas, WebGL, shaders, frame sequences, or persistent media.
- Read each domain reference before consulting references/examples.md. Recipes illustrate implementation after a decision; they do not replace domain instructions.
What ships with it
13 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.
- creative-web-development-portable.md 17 KB
- references/canvas-and-particles.md 10 KB
- references/concept-evaluation.md 5.5 KB
- references/creative-direction.md 8.6 KB
- references/examples.md 23 KB
- references/hybrid-3d-cinematics.md 11 KB
- references/motion-and-scroll.md 19 KB
- references/performance-and-profiling.md 12 KB
- references/shaders-and-glsl.md 7.3 KB
- references/story-engineering.md 5.6 KB
- references/terminology.md 22 KB
- references/threejs-and-r3f.md 13 KB
- synthesis-report.md 8.5 KB
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.
- 5d ago First seen · 201 lines · 42 tokens per session scan A dd97f94028e1
creative-web-development is a skill published in the GitHub repository J-StaR-Films-Studios/VibeCode-Protocol-Suite (24 stars, last pushed 4d ago), licensed ISC. It adds 42 tokens to every session and 2,658 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 2026-09-03.
Other skills, from other repositories
remotion-production-guide
Remotion (React video framework) production guide with Apple-style design rules. Use when: 'create video with remotion', 'remotion project', 'render video', 'product demo video', 'animated video', 'video from code'. Covers project setup, animation library, spring presets, typography rules, color palettes, pacing…
html-deck-builder
Plan and build browser-editable HTML presentations with narrative contracts, responsive slide layouts, keyboard navigation, offline-safe assets, and render verification. Use when the final presentation should be an HTML file or browser-based deck rather than a native PPTX.
remotion-to-hyperframes
Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW…
lottie
Lottie and dotLottie adapter patterns for HyperFrames. Use when embedding lottie-web JSON animations, .lottie files, @lottiefiles/dotlottie-web players, registering instances on window.hfLottie, or making After Effects exports deterministic in HyperFrames.
three
Three.js and WebGL adapter patterns for HyperFrames. Use when creating deterministic Three.js scenes, WebGL canvas layers, AnimationMixer timelines, camera motion, shader-driven visuals, or canvas renders that respond to HyperFrames hf-seek events.
remotion-best-practices
Remotion video composition best practices for searchpo. Use when editing src/ components, configuring rendering, optimizing video output, or adding animations/effects to the Remotion pipeline.