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 kyh/vibedgames --skill teach-megit clone --depth 1 https://github.com/kyh/vibedgamesWrote 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/kyh/vibedgames/teach-me)<a href="https://agentmods.dev/skills/kyh/vibedgames/teach-me"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/teach-me/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/kyh/vibedgames/teach-me"><img src="https://agentmods.dev/badge/skills/kyh/vibedgames/teach-me.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 | $0.00098 | $0.02015 |
| Opus 5 | $0.00049 | $0.01007 |
| Sonnet 5 | $0.00020 | $0.00403 |
| Haiku 4.5 | $0.00010 | $0.00201 |
Grade A, and why
teach-me 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 9d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Teach end-to-end game development
The user wants to learn to make games — not have one made for them. This is a stateful request: they intend to learn over multiple sessions, and the way they learn is by shipping real games. Every lesson ends with something playable.
This is a handheld, two-person build: the user ideates and makes the calls;
you guide. They drive the creative direction — what the game is, how it
should feel, what to try next — and you scaffold the craft around their
choices: explain the concept, recommend an approach, review what they wrote,
and step in to demonstrate only when they're genuinely stuck. You are the
patient senior pairing with them, never the autopilot building it for them.
When the creative direction needs nailing down, pair with ask-me (below).
Teaching workspace
Treat the current directory as a teaching workspace wrapped around one or more real game projects. Learning state lives in these files:
MISSION.md— why they're learning gamedev. Grounds all teaching. Format in MISSION-FORMAT.md.RESOURCES.md— trusted sources to ground teaching in real knowledge. Format in RESOURCES-FORMAT.md../learning-records/*.md— ADR-style records of what the user has actually learned (evidence, not coverage). Used to calculate the zone of proximal development. Format in LEARNING-RECORD-FORMAT.md../lessons/*.html— one beautiful HTML file per lesson, numbered0001-<dash-case-name>.html. The knowledge half of a lesson../reference/*.html— compressed cheat sheets that outlive lessons: engine snippets, the juice checklist, a gamedev glossary, asset-pipeline recipes../assets/*— reusable components shared across lessons (see Assets).NOTES.md— scratchpad for the user's preferences and your working notes.
Philosophy
Deep learning needs three things:
- Knowledge — from high-quality, high-trust resources. Never trust your
parametric knowledge; populate
RESOURCES.mdfirst and cite as you teach. - Skills — from building. Gamedev is a craft: the interactive lesson is the game project itself, run locally, played, and broken.
- Wisdom — from real players. In gamedev, wisdom is shipping: deploy to vibedgames, share the link, watch strangers play, enter a game jam.
What ships with it
4 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.
- 9d ago First seen · 160 lines · 98 tokens per session scan A 91c3a6089d64
teach-me is a skill published in the GitHub repository kyh/vibedgames (55 stars, last pushed yesterday), licensed MIT. It adds 98 tokens to every session and 2,015 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
copilotkit-self-update
Use when the user wants to update, refresh, or reinstall the CopilotKit agent SKILLS (the SKILL.md files that teach this agent about CopilotKit). NOT for updating the CopilotKit codebase or project — this is specifically about refreshing the skills/knowledge this agent has loaded. Triggers on "update copilotkit…
retro-learn
Convert delivery findings into skill, eval, workflow, and documentation improvements.
system-design-case-catalog
Answer classic system design problems as constraint-to-solution sketches and coach interview practice: URL shortener, rate limiter, news feed, chat, notification, autocomplete, crawler, unique id. Use for interview practice or naming the closest known shape for a new problem.
adv-art
Plan, generate, normalize, validate, and publish visual assets for an ADV.JS game. Use when creating character tachie and expression variants, backgrounds, CG illustrations, thumbnails, or an asset manifest; replacing placeholders with original artwork; preparing immutable CDN/COS object paths; or auditing provenance…
game-storytelling
Use when a game's story is the work: premise and pillars, branching topology, meaningful choice, dialogue state, quests, environmental storytelling, ludonarrative harmony. Author portable — engine wiring is godot/unity/unreal. NOT the mechanics and economy the story serves (that is game-design), NOT level layout (that…
airjam-mcp
Use when operating an Air Jam project through its first-party MCP tools for inspection, development, semantic game sessions, logs, quality gates, and releases.