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 create-openbitfun-skingit 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/create-openbitfun-skin)<a href="https://agentmods.dev/skills/gcwing/bitfun/create-openbitfun-skin"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/create-openbitfun-skin.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 | $0.00090 | $0.01428 |
| Opus 5 | $0.00045 | $0.00714 |
| Sonnet 5 | $0.00018 | $0.00286 |
| Haiku 4.5 | $0.00009 | $0.00143 |
Grade A, and why
create-openbitfun-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 yesterday.
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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenBitFun Appearance Authoring
Use this Skill as the authority for what a OpenBitFun skin may change and how that change is represented. Let the user's assets, product direction, and the selected example determine the visual design.
The bundled registry and package references define capabilities. Files under examples/ define optional style choices; they never expand the contract or prescribe coverage for another skin.
Route the task
- For a new or repaired package, read authoring-workflow.md and package-contract.md.
- For renderer configuration, also read renderer-contracts.md.
- For generated video or WebP assets, also read media-quality-policy.md.
- For a style-specific design, load only the closest example after reading the parent workflow.
- For import failures, inspect the issue path, query that surface, and repair the sparse manifest instead of copying another package.
- For OpenBitFun contract changes, synchronize the registry before changing examples or skins.
Discover the exposed surface
Run commands from this Skill directory:
python scripts/openbitfun_appearance.py contract list components
python scripts/openbitfun_appearance.py contract list scenes
python scripts/openbitfun_appearance.py contract list renderers
python scripts/openbitfun_appearance.py contract show components <component-id>
python scripts/openbitfun_appearance.py contract show scenes <scene-id>
python scripts/openbitfun_appearance.py contract properties
python scripts/openbitfun_appearance.py contract tokens theme
python scripts/openbitfun_appearance.py contract tokens widget
Only author registered surfaces, Parts, facets, states, renderer adapters, tokens, and Style IR properties returned by these commands. A Part descriptor may further restrict its allowed properties.
A component owns only the Parts returned for that component. Nested visual owners expose their own component ids and must be styled through those ids. Do not infer Parts from DOM structure, another skin, or an example surface plan.
What ships with it
23 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.
- agents/openai.yaml 299 B
- examples/cinematic-animated-wallpaper/references/default-palette.json 516 B
- examples/cinematic-animated-wallpaper/references/palette-contract.md 1.1 KB
- examples/cinematic-animated-wallpaper/references/style-playbook.md 10.0 KB
- examples/cinematic-animated-wallpaper/references/surface-plan.json 23 KB
- examples/cinematic-animated-wallpaper/scripts/build_assets.py 7.3 KB runs code
- examples/cinematic-animated-wallpaper/scripts/build_cinematic_skin.py 18 KB runs code
- examples/cinematic-animated-wallpaper/scripts/cinematic_recipe.py 18 KB runs code
- examples/cinematic-animated-wallpaper/scripts/scaffold_cinematic.py 3.4 KB runs code
- examples/cinematic-animated-wallpaper/SKILL.md 6.5 KB
- references/appearance-registry.json 360 KB
- references/authoring-workflow.md 3.7 KB
- references/media-quality-policy.md 2.8 KB
- references/package-contract.md 5.7 KB
- references/renderer-contracts.md 1.6 KB
- references/style-example-contract.md 2.6 KB
- scripts/build_support.py 6.1 KB runs code
- scripts/media_support.py 20 KB runs code
- scripts/openbitfun_appearance.py 94 KB runs code
- scripts/sync_registry.py 7.5 KB runs code
- scripts/test_cinematic_tools.py 9.6 KB runs code
- scripts/test_openbitfun_appearance.py 6.9 KB runs code
- scripts/verify_host.py 7.5 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.
- yesterday First seen · 117 lines · 90 tokens per session scan A bd8362043748
create-openbitfun-skin is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed yesterday), licensed MIT. It adds 90 tokens to every session and 1,428 once invoked, about $0.0005 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 2026-09-06.
Other skills, from other repositories
task-management
Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID…
task-coordination
Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.
liquid-glass
Apple Liquid Glass design system. Use when building UI with translucent, depth-aware glass morphism following Apple's design language. Provides CSS tokens, component patterns, dark/light mode, and animation specs.
mcporter
Discover and call MCP Server tools via the mcporter CLI. Use when your coordinator notifies you about new MCP tools, or when you need to call external APIs. Includes workflow for generating skill documentation for new MCP servers.
project-management
Use when admin asks to start a multi-worker project, when a Worker @mentions you with task completion in a project room, when project plan changes are needed, or when a blocked task needs resolution.
critique
Evaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or…