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 commands/summerengine/summer-engine-agent/gameskillgit clone --depth 1 https://github.com/SummerEngine/summer-engine-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/commands/summerengine/summer-engine-agent/gameskill)<a href="https://agentmods.dev/commands/summerengine/summer-engine-agent/gameskill"><img src="https://agentmods.dev/badge/commands/summerengine/summer-engine-agent/gameskill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.02094 |
| Opus 5 | $0.00000 | $0.01047 |
| Sonnet 5 | $0.00000 | $0.00419 |
| Haiku 4.5 | $0.00000 | $0.00209 |
Grade A, and why
gameskill 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 4d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are capturing what we just learned in this game-development session into Summer Engine's skill library, so the next agent (and every Summer user) gets to start where we ended.
This is the meta-skill: the loop that turns ad-hoc fixes into durable, reusable expertise.
What "Summer Engine" is, so you're grounded
Three repos, one ecosystem:
~/development/SummerEngine— the Summer Engine desktop source and the canonical CLI. The C++ engine is maintained against the upstream Godot Engine codebase; the Summer-owned module lives atmodules/1summer_engine/. The Summer CLI lives attools/summer-cli/and is normally invoked withnpx -y summer-engine@latest. It installs, signs in, creates, and runs Summer projects and can install the current Summer skill bundle for supported agents.~/development/PublicSummerEngine— the web app at summerengine.com. Has its own AI skill stores atsrc/lib/ai/skills/bundled/andpublic/knowledge/summer/skills/for the in-browser chat agent. ALSO has its own MCP-style consumers of the engine API (src/lib/bridge/direct-executor.ts,src/lib/ai/tools/run-and-verify.ts) which call the same engine endpoints the CLI does.- The active Summer game project — usually
~/development/<game-name>or whatever game we were just working on. The live compatibility line comes from Summer Engine, not this prompt. Real working code in this repo is the gold standard for examples.
The skill system is the value flywheel: every game we ship teaches lessons → the lessons become skills → the next user (or AI) starts smarter. Your job here is to close that loop for what we just did.
Cross-repo change awareness — read this before any non-trivial fix
When the lesson is "the engine should expose more / behave differently," the change usually crosses repo boundaries. Map the layers before you edit:
[active game] → calls MCP / web app
↓
[summer-cli MCP server (TypeScript)] → calls /api/ops + /api/state/* on the engine
↓
[Summer Engine binary (C++ in SummerEngine repo)] — source of truth for what the API can return
[PublicSummerEngine web app (TypeScript)] → also calls the same engine endpoints via direct-executor or Redis bridge
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.
- 4d ago First seen · 113 lines · 0 tokens per session scan A 5434c71dd43a
gameskill is a command published in the GitHub repository SummerEngine/summer-engine-agent (57 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,094 tokens. 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 commands, from other repositories
review-impl
On-demand adversarial implementation review. Invoke when POST-REVIEW needs a deeper look or after COMMIT when something feels off.
amaw
Enable AMAW (Autonomous Multi-Agent Workflow) mode for the current task. Spawns cold-start sub-agents at REVIEW + POST-REVIEW phases instead of using main-session self-review.
play-dashboard
Play in the dashboard — the local viewer becomes your play surface, with a live AI DM beside it.
world-play
Drop into a living world and adventure — the DM generates the story live within its canon.
campaign-new
Start a brand-new WorldOS campaign — create your character, meet your AI companion, and begin an adventure.
session-start
Begin or resume play — loads your campaign, recaps "Previously on…", and hands the table to the DM.