BitFun is a desktop AI agent that turns tasks into interactive mini-apps while also writing code, creating documents, and controlling computers. It is for software development and general desktop work across Windows, macOS, and Linux. Its catalogue entries extend the agent with skills, agents, and instructions.
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 GCWing/BitFun --skill cinematic-animated-wallpapergit clone --depth 1 https://github.com/GCWing/BitFunWrote 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/gcwing/bitfun/cinematic-animated-wallpaper)<a href="https://agentmods.dev/skills/gcwing/bitfun/cinematic-animated-wallpaper"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/cinematic-animated-wallpaper/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/gcwing/bitfun/cinematic-animated-wallpaper"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/cinematic-animated-wallpaper.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 | $0.00075 | $0.01362 |
| Opus 5 | $0.00037 | $0.00681 |
| Sonnet 5 | $0.00015 | $0.00272 |
| Haiku 4.5 | $0.00007 | $0.00136 |
Grade A, and why
create-openbitfun-cinematic-wallpaper-skin 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 2d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic animated-wallpaper recipe
Load the parent create-openbitfun-skin Skill first. The parent registry and package references define what can be changed; this example defines one optional visual strategy.
Do not reuse this example's asset roles, crop defaults, palette, opacity, or material choices unless they fit the user's artwork and intent. Its surface-plan.json is an example style selection validated against one registry revision, not a list of all current Appearance surfaces. Re-query the parent registry whenever the host checkout or bundled snapshot changes.
Read style-playbook.md for visual decisions and palette-contract.md before creating a custom palette. Read the parent media-quality-policy.md before overriding video or WebP quality.
Style strategy
This recipe uses:
- a host-managed VP9 WebM background with an image poster;
- source-derived artwork for floating surfaces, sidebars, cards, and dialogs;
- translucent cinematic materials over the artwork;
- a semantic palette shared by Style IR and renderer adapters;
- broad surface coverage suitable for an immersive character-led skin.
Keep the built-in Appearance for any owner that does not benefit from this treatment. Query the parent registry before adding, removing, or changing a selected surface.
Output layout
Keep the importable project isolated from source and report files:
<skin-root>/
package/
appearance.json
assets/
background.webm
floating.webp
sidebar.webp
card-detail.webp
card-portrait.webp
dialog.webp
preview.webp
sources/
palette.json
surface-plan.json
contact-sheet.png
asset-preview-sheet.png
<skin-id>.openbitfun-appearance
host-verification.json
skin-build.json
runtime-checklist.json
Validate and build only <skin-root>/package. Reports and source files inside that directory invalidate the project.
What ships with it
8 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.
- references/default-palette.json 516 B
- references/palette-contract.md 1.1 KB
- references/style-playbook.md 10.0 KB
- references/surface-plan.json 23 KB
- scripts/build_assets.py 7.3 KB runs code
- scripts/build_cinematic_skin.py 18 KB runs code
- scripts/cinematic_recipe.py 18 KB runs code
- scripts/scaffold_cinematic.py 3.4 KB runs code
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.
- 2d ago Changed · +3 tokens per session d5df4a4153e2
- 9d ago First seen · 135 lines · 72 tokens per session scan A b58f04273d6e
create-openbitfun-cinematic-wallpaper-skin is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed 2d ago), licensed MIT. It adds 75 tokens to every session and 1,362 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
desktop-brand-builder
Generate a branded Qwen Code desktop package from the Tauri desktop shell using a minimal brandId and logo. Use when the user wants a custom, white-label, or rebranded desktop client, installer, DMG/EXE/AppImage/deb, or one-click brand build on top of packages/desktop-shell.
drawio-diagram
A tool for creating editable Draw.io diagrams, a file format used for flowcharts, system diagrams, and model illustrations.
memstack-content-youtube-script
Use this skill when the user says 'YouTube script', 'video script', 'write script for YouTube', 'YouTube video outline', or is creating scripted content for a YouTube video with hooks, chapters, and CTAs. Do NOT use for TikTok/Reels short-form scripts or webinar presentations.
memstack-content-tiktok-script
Use this skill when the user says 'TikTok script', 'TikTok video', 'Reels script', 'Shorts script', 'short-form video', or needs timestamped scripts with hooks, visual cues, and captions for 15-60 second videos. Do NOT use for Twitter threads or webinar scripts.
memstack-marketing-facebook-ad
Use this skill when the user says 'facebook ad', 'FB ad', 'Meta ad', 'Instagram ad', or needs social media ad copy with targeting, creative direction, and A/B test plans for Meta Ads Manager. Do NOT use for Google search ads or organic social content.
brand-identity
Brand strategy and identity design for businesses and products. Use when creating brand guidelines, developing visual identity systems, or defining brand positioning.