II-Agent is an open-source framework and AI agent for building applications, conducting research, and automating workflows from natural-language prompts. Developers, research teams, and enterprises use it to create mobile apps, websites, illustrated books, media, research outputs, and integrations with external services. The catalogue skills and instructions provide workflows and integrations for using II-Agent.
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 Intelligent-Internet/ii-agent --skill building-mobile-gamegit clone --depth 1 https://github.com/Intelligent-Internet/ii-agentWrote 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/intelligent-internet/ii-agent/building-mobile-game)<a href="https://agentmods.dev/skills/intelligent-internet/ii-agent/building-mobile-game"><img src="https://agentmods.dev/badge/skills/intelligent-internet/ii-agent/building-mobile-game/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/intelligent-internet/ii-agent/building-mobile-game"><img src="https://agentmods.dev/badge/skills/intelligent-internet/ii-agent/building-mobile-game.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 | $0.00091 | $0.01100 |
| Opus 5.5 | $0.00036 | $0.00440 |
| Sonnet 5.5 | $0.00018 | $0.00220 |
| Haiku 4.5 | $0.00009 | $0.00110 |
Grade A, and why
building-mobile-game 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mobile Game Workflow
References
./references/setup-and-loop.md-- Expo bootstrap, worklets setup, engine selection, game loop order, physics rules, packages, and performance checks./references/assets-and-animation.md-- sprite-sheet prompt templates, extraction workflow, naming, animation state mapping, and validation checklist./scripts/extract_sprites.py-- connected-component sprite extractor with background removal and optional frame normalization./scripts/normalize_animation_frames.py-- shared-scale frame normalizer with optional anchor frame locking for existing characters
Mandatory Reading Order
For any new mobile game task, read both reference files before planning implementation or calling project tools:
- Read
./references/setup-and-loop.mdfirst. - Read
./references/assets-and-animation.mdsecond. - Only after both references have been read should you choose libraries, plan gameplay, generate assets, or start coding.
Do not stop after reading only setup-and-loop.md. The asset reference is also mandatory for almost every real game because it covers sprite-sheet prompting, extraction, and normalization.
The only acceptable exception is a deliberately art-free prototype that uses simple geometric placeholder shapes and no image generation. When in doubt, read both references anyway.
Quick Start
- Read
./references/setup-and-loop.md, then read./references/assets-and-animation.md. - Start from
mobile_app_init(..., example="with-reanimated", with_tailwind=False)for animation-heavy or gesture-heavy game projects. - Install
[email protected]and put"react-native-worklets/plugin"last inbabel.config.js. Never add"react-native-reanimated/plugin". - Choose the lightest rendering stack that can support the mechanic:
react-native-game-enginefor most 2D arcade or puzzle loops@shopify/react-native-skiafor custom 2D drawing and effectsexpo-glplusthreefor 3D or GL scenesmatter-jsonly when the game truly needs richer physics
- Build gameplay in this order: input, movement, collisions, scoring or lives, pause or restart, then polish.
- Ask
generate_imagefor one whole animation strip at once, not one frame at a time, so character identity and proportions stay consistent. - Split raw strips with
./scripts/extract_sprites.py, then standardize them with./scripts/normalize_animation_frames.pywhen the game needs fixed frame sizes or an exact existing idle anchor. - Verify the game on Expo web and on mobile before calling the feature done.
What ships with it
5 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.
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 First seen · 68 lines · 91 tokens per session scan A 6039c4292e51
building-mobile-game is a skill published in the GitHub repository Intelligent-Internet/ii-agent (3,392 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,100 once invoked, about $0.0004 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
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
company-employee
The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or…
company-ceo
Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream, review tickets and report to the board in the all-hands channel.
a2ui
Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a callout, a Mermaid diagram, a weather card, a live clock or countdown, a dashboard of gauges for a quota, a budget or a…
penguin-plugin
Use for workbenches — the tabs and pages beside the chat, with server code behind them, that an Agent keeps in its own workbenches/ folder inside PenguinHarness — building one, changing it, showing it as the whole app, restoring an earlier version, and removing a tab or a whole workbench when the user wants the custom…