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 gstack-autoplangit 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/gstack-autoplan)<a href="https://agentmods.dev/skills/gcwing/bitfun/gstack-autoplan"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/gstack-autoplan/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/gstack-autoplan"><img src="https://agentmods.dev/badge/skills/gcwing/bitfun/gstack-autoplan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 165 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 32 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 685 Skill allows unbounded resource consumption (API calls, storage, compute). Without rate limits or quotas, a compromised or misbehaving agent can cause denial-of-service or cost overruns.Fix: Set explicit rate limits, timeouts, and resource quotas for API calls, file operations, and compute. Implement circuit breakers for runaway loops.
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 | $0.00152 | $0.09459 |
| Opus 5.5 | $0.00061 | $0.03784 |
| Sonnet 5.5 | $0.00030 | $0.01892 |
| Haiku 4.5 | $0.00015 | $0.00946 |
Grade A, and why
autoplan 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 1mo 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 — 823 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/autoplan — Auto-Review Pipeline
One command. Rough plan in, fully reviewed plan out.
/autoplan reads the full CEO, design, eng, and DX review skill files from disk and follows them at full depth — same rigor, same sections, same methodology as running each skill manually. The only difference: intermediate AskUserQuestion calls are auto-decided using the 6 principles below. Taste decisions (where reasonable people could disagree) are surfaced at a final approval gate.
The 6 Decision Principles
These rules auto-answer every intermediate question:
- Choose completeness — Ship the whole thing. Pick the approach that covers more edge cases.
- Boil lakes — Fix everything in the blast radius (files modified by this plan + direct importers). Auto-approve expansions that are in blast radius AND < 1 day CC effort (< 5 files, no new infra).
- Pragmatic — If two options fix the same thing, pick the cleaner one. 5 seconds choosing, not 5 minutes.
- DRY — Duplicates existing functionality? Reject. Reuse what exists.
- Explicit over clever — 10-line obvious fix > 200-line abstraction. Pick what a new contributor reads in 30 seconds.
- Bias toward action — Merge > review cycles > stale deliberation. Flag concerns but don't block.
Conflict resolution (context-dependent tiebreakers):
- CEO phase: P1 (completeness) + P2 (boil lakes) dominate.
- Eng phase: P5 (explicit) + P3 (pragmatic) dominate.
- Design phase: P5 (explicit) + P1 (completeness) dominate.
Decision Classification
Every auto-decision is classified:
Mechanical — one clearly right answer. Auto-decide silently. Examples: run codex (always yes), run evals (always yes), reduce scope on a complete plan (always no).
Taste — reasonable people could disagree. Auto-decide with recommendation, but surface at the final gate. Three natural sources:
- Close approaches — top two are both viable with different tradeoffs.
- Borderline scope — in blast radius but 3-5 files, or ambiguous radius.
- outside-voice sub-agent disagreements — codex recommends differently and has a valid point.
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.
- 1mo ago Changed df1ccc2df040
- 1mo ago First seen · 823 lines · 152 tokens per session scan A d5681d893468
autoplan is a skill published in the GitHub repository GCWing/BitFun (2,077 stars, last pushed 1mo ago), licensed MIT. It adds 152 tokens to every session and 9,459 once invoked, about $0.0006 per session on Opus 5.5. 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…