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 | $0.00046 | $0.00550 |
| Sonnet 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 11d 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.
- 11d 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 (3,382 stars, last pushed 25d ago), licensed Apache-2.0. It adds 91 tokens to every session and 1,100 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 2026-08-30.
Other skills, from other repositories
agentfield-use
Whenever you have a discrete task to perform — one the user delegated, or one that arose inside your own work — check FIRST whether an installed AgentField agent covers it, and offload to it by default when one does. Coverage, not task size, is the test: even a small job goes to a covering agent. The check is cheap …
agent-optimization
Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.
agent-evaluation
Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
browser-workflow-skill-builder
Create robust browser automation skills for sites like LinkedIn, X/Twitter, YouTube, Stripe, or other logged-in web apps by saving page context, analyzing HTML/CSS, writing skill-local JS extract/verify scripts, and using CSS selector actions with screenshot verification.
cli-skill-design
Design a co CLI surface and its SKILL.md together so an agent can drive it without guessing — every command ends by naming the next one, --help lists everything, and every failure says what to run instead. Use when adding a new CLI command group, writing or rewriting a SKILL.md for one, or auditing an existing one.