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-designnpx skills add phuonghx/aim-cli --skill game-designgit 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 | $0.00090 | $0.00829 |
| Opus 5 | $0.00045 | $0.00415 |
| Sonnet 5 | $0.00018 | $0.00166 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
game-design 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Game Design
Decisions about what makes a game fun and how players grow through it. The throughline: prove fun by playing, not by planning.
The Core Loop
The 30-second test
If a game isn't enjoyable in a tight repeating cycle, no amount of content saves it. The cycle:
Act → Get feedback → Earn a reward → Go again.
The player does something, the game answers clearly, that answer feels good, and they immediately want another go.
How it looks per genre
| Genre | The loop |
|---|---|
| Platformer | Run → jump → land → collect |
| Shooter | Aim → fire → kill → loot |
| Puzzle | Observe → reason → solve → move on |
| RPG | Explore → fight → level up → upgrade gear |
The Design Document
Sections worth having
| Section | Captures |
|---|---|
| Pitch | The whole game in one sentence |
| Core loop | The 30-second gameplay cycle |
| Mechanics | How each system actually works |
| Progression | How the player moves forward |
| Art style | The visual direction |
| Audio | The sound direction |
How to treat it
- Keep it alive — revise it as the game changes; a stale GDD lies.
- Show, don't just tell — diagrams and reference images communicate faster than paragraphs.
- Stay small early — scope down first; expand only once the core proves out.
What Drives Players
Motivation archetypes
| Player | Chasing |
|---|---|
| Achiever | Goals, completion, 100% |
| Explorer | Discovery, hidden corners, secrets |
| Socializer | People, interaction, community |
| Killer | Competition, beating others, dominance |
Reward timing
| Schedule | Feel | Where it fits |
|---|---|---|
| Fixed | Predictable, dependable | Milestone payouts |
| Variable | Compelling, hard to put down | Loot drops |
| Ratio (effort-based) | Earned through work | Grind-oriented systems |
Difficulty and Flow
Keep the player in the channel between boredom and panic:
- Too hard → frustration → they quit.
- Too easy → boredom → they quit.
- Tuned right → flow → they stay engaged.
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 · 113 lines · 90 tokens per session scan A ff00f6e55614
game-design is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 90 tokens to every session and 829 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 2026-08-31.
Other skills, from other repositories
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
memory-audit-pattern-extraction
模式提取与失效解药分析。当发现多条记忆在讲同一个教训，或发现自己在一而再再而三地犯同样的错误时使用。.
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).
presentation-deck
Structure a design presentation for a specific audience and decision. Use when presenting internally. For a portfolio narrative use case-study; for the written argument use design-rationale.