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 agentmods add skills/phuonghx/aim-cli/game-developmentnpx skills add phuonghx/aim-cli --skill game-developmentgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00088 | $0.01305 |
| Opus 5 | $0.00044 | $0.00652 |
| Sonnet 5 | $0.00018 | $0.00261 |
| Haiku 4.5 | $0.00009 | $0.00130 |
Grade A, and why
game-development 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Development
A hub skill: it carries the engine-neutral fundamentals every game shares and hands off to a focused sub-skill once the project's shape is clear.
How to route
Pick the sub-skill that matches what the question is really about. Most projects touch several.
By target hardware
- Runs in a browser (HTML5 / WebGL / WebGPU) →
web-games - Phones and tablets (iOS, Android) →
mobile-games - Desktop and console (Steam, PlayStation, Xbox, Switch) →
pc-games - Headsets and passthrough (Quest, PCVR, ARKit/ARCore) →
vr-ar
By visual dimension
- Flat: sprites, tiles, parallax →
2d-games - Volumetric: meshes, materials, lights →
3d-games
By discipline
- Systems, economy, pacing, the design doc →
game-design - Networking, replication, authority →
multiplayer - Look, asset pipeline, rigging and animation →
game-art - Sound effects, score, reactive mixing →
game-audio
Fundamentals that apply everywhere
1. The simulation loop
A game is a loop that samples input, advances the world, and paints a frame:
read input → step simulation (fixed dt) → draw (interpolated)
Decouple the two clocks. Run gameplay and physics at a fixed step (commonly 30–60 Hz) so behavior is deterministic and stable; render as often as the display allows and interpolate between the last two simulation states so motion looks smooth even when the two rates disagree.
2. Choosing a structure
| Approach | Reach for it when | Concrete case |
|---|---|---|
| Finite state machine | An entity has a handful of clear modes | Door: closed → opening → open → closing |
| Object pool | Things spawn and die constantly | Shell casings, hit sparks, projectiles |
| Event bus / observer | Systems must react without knowing each other | Pickup grabbed → score, SFX, and HUD all respond |
| Entity-component-system | Tens of thousands of like entities | Bullet-hell waves, swarm units |
| Command objects | You need replay, netcode, or undo | Recording a speedrun ghost |
| Behavior tree | Branching, authorable AI | A guard that patrols, investigates, then chases |
What ships with it
10 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.
- yesterday First seen · 137 lines · 88 tokens per session scan A 81e5d79d2167
game-development is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 1,305 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
motion-system
Define motion tokens — durations, easing vocabulary, and reduced-motion handling — for consistency product-wide. Use when standardising motion across a system. For crafting one specific animation, use animation-principles (interaction-design).
case-study
Craft a portfolio case study with narrative arc, process evidence, and outcomes. Use when telling a project's story to an external audience. For an internal stakeholder deck, use presentation-deck.
icon-system
Specify an icon system — grid, sizing, stroke weight, naming, categories, and implementation. Use when standardising iconography. For broader illustration, use illustration-style (ui-design).
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…
new-feedback
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-.md with the five-stage template (R9 — numbers are…