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 pr-review-canvasgit 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/pr-review-canvas)<a href="https://agentmods.dev/skills/gcwing/bitfun/pr-review-canvas"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/pr-review-canvas.svg" alt="Measured on agentmods" 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 | $0.00064 | $0.01301 |
| Opus 5 | $0.00032 | $0.00651 |
| Sonnet 5 | $0.00013 | $0.00260 |
| Haiku 4.5 | $0.00006 | $0.00130 |
Grade A, and why
pr-review-canvas 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Review Canvas
Use this skill to produce a session-scoped OpenBitFun Canvas that helps a reviewer understand a PR quickly. The artifact should reorganize the diff for reviewer comprehension, not mirror file-tree order. It should look and feel like a Cursor Canvas review: compact metadata, focused diff stats, pill filters, file diff cards, tables, callouts, traces, and reviewer-facing notes.
Read and follow openbitfun-canvas first. It defines the Canvas tool workflow, source rules, SDK surface, and design constraints.
Inputs
Gather the change set before writing TSX:
- If the user gives a GitHub PR URL or number, use
gh pr viewandgh pr diffwhen available. - If the user explicitly asks for current local changes, use
git diff,git diff --stat, andgit diff --name-status. - If the user gives a branch/range, use that exact range.
- If the diff source is ambiguous, ask which PR, branch, or local diff to review. Do not guess from the current branch.
Collect:
- PR title, repo, number/link, author, base/head, status, and update time when available.
- File stats, additions/deletions, generated/mechanical files, test files, and risky files.
- Core hunks with enough context to understand behavior.
- Verification commands or CI checks when visible.
Canvas Structure
Organize by review importance, not file-tree order:
- Review map: PR identity, scope, diff stats, state, top risks.
- Core logic: behavior changes first, with file cards and
DiffViewsnippets. - Wiring and integration: routes, registration, config, dependency injection, feature flags.
- Tests and verification: added/changed tests, missing coverage, commands run or expected.
- Mechanical changes: imports, renames, generated files, formatting. Summarize in compact lists or tables instead of dumping.
- Reviewer checklist: concrete questions, risk callouts, suggested review focus.
The first screen should already be useful to a reviewer. Lead with the behavior that matters most and one compact map of the change: risk summary, file groups, or a before/after flow. Do not make the reviewer scroll past metadata before seeing the core change.
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 Changed · +1 tokens per session e76f2c1c6200
- 8d ago First seen · 107 lines · 63 tokens per session scan A d2f46bca3c03
pr-review-canvas is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,301 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 2026-08-30.
Other skills, from other repositories
memstack-development-code-reviewer
Use this skill when the user says 'review code', 'code review', 'check my code', 'audit this', 'review PR', 'review changes', 'what's wrong with this', or is requesting a structured review of code quality, security, performance, or maintainability. Do NOT use for refactoring plans or test generation.
shard
Use when the user says 'shard this', 'split file', or when working with files over 1000 lines.
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.
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.
find-simplifications
Use for a periodic repo-wide sweep of qwen-code for accumulated excess surface — dead components and files, orphaned locale keys, exports nothing consumes, added-then-removed scaffolding — filing candidates on a tracking issue and landing only what a maintainer has said yes to. Repo-wide and evidence-first; every…