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 openbitfun-frontend-devgit 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/openbitfun-frontend-dev)<a href="https://agentmods.dev/skills/gcwing/bitfun/openbitfun-frontend-dev"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/openbitfun-frontend-dev.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 | $0.00060 | $0.00772 |
| Opus 5 | $0.00030 | $0.00386 |
| Sonnet 5 | $0.00012 | $0.00154 |
| Haiku 4.5 | $0.00006 | $0.00077 |
Grade A, and why
openbitfun-frontend-dev 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenBitFun frontend customization
Use this workflow only for the running OpenBitFun desktop client's own frontend. It is not for a website in the user's workspace, a MiniApp, or a remote OpenBitFun host.
Required workflow
- Call
FrontendWorkbenchwithaction: "prepare". - Edit only the returned draft directory. Never edit the packaged resource directory, active revision, state file, or another draft.
- Read the returned
openbitfun-creation-api.md. Editopenbitfun-creation.css,openbitfun-creation.js, and optionalcreation-assets/only. The draft contains no application bundle orindex.html. It needs no source repository, Node.js, dependencies, compiler, or rebuild. CSS loads last; JavaScript is a browser ES module exportingdefault function activate(ui), called after the real shell renders. Useui.mountslots and documented semantic selectors; return cleanup for your listeners/timers. - Call
FrontendWorkbenchwithaction: "apply", setting itsdraft_idinput to the exact returneddraftId. - Before calling
apply, tell the user to inspect the live preview and use the immutable review window. Its Keep button remains disabled until both the real shell and customization activate; the 15-second countdown starts after readiness. - Read the final
applyresult. Onlystatus: "confirmed"means the revision was kept;status: "rolled_back"includes the reason. UseFrontendWorkbench statusfor later inspection, not direct reads ofstate.json. - Use
FrontendWorkbench inspectto check actual mount slots, registered commands and diagnostics. For reusable capabilities, register commands withui.commands.register, compose persistentui.statewithui.events, and verify behavior withFrontendWorkbench invokeusing the discovered schema. Commands and subscriptions follow activation; state survives code rollback. These commands run in the visible local client, not a headless service.
apply is a two-phase transaction: the confirmed active revision remains authoritative while the candidate is previewed, then user confirmation commits it. If the app shell cannot report readiness, the user does not confirm within 15 seconds, or OpenBitFun exits, the host restores the prior revision. Never bypass or emulate readiness or the confirmation timer in editable page JavaScript.
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 · 37 lines · 60 tokens per session scan A 288025e666a7
openbitfun-frontend-dev is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 772 once invoked, about $0.0003 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…