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 AlterLab-IEU/AlterLab_GameForge --skill game-code-reviewgit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab_GameForgeWrote 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/alterlab-ieu/alterlab_gameforge/game-code-review)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-code-review"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-code-review/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/alterlab-ieu/alterlab_gameforge/game-code-review"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-code-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00096 | $0.05116 |
| Opus 5.5 | $0.00038 | $0.02046 |
| Sonnet 5.5 | $0.00019 | $0.01023 |
| Haiku 4.5 | $0.00010 | $0.00512 |
Grade A, and why
game-code-review 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 1mo 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 — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlterLab GameForge -- Game Code Review Workflow
Game code has failure modes that web code does not. A web app that allocates memory in a request handler costs you some latency. A game that allocates memory in an update loop costs you frame drops that players feel in their hands. A web app with a state management bug shows stale data. A game with a state management bug lets the player walk through walls or fire invisible bullets. Celeste's codebase is legendary precisely because Maddy Thorson and Noel Berry treated frame-perfect input handling as a first-class engineering concern -- and the result is the tightest platformer ever shipped.
This workflow reviews game code through two lenses simultaneously: standard software quality (naming, structure, testing, documentation) and game-specific correctness (frame independence, hot path performance, state machine integrity, resource lifecycle). Both lenses matter. Factorio maintains a million-entity simulation at 60fps because Wube Software treats architecture as a gameplay feature. Ignoring either lens produces code that is either well-structured but broken at runtime, or high-performing but unmaintainable.
Purpose & Triggers
Use this workflow when:
- A developer asks "review my game code" or "check my architecture"
- Before merging a significant feature branch
- When debugging a performance issue and suspecting structural causes
- When a new developer joins and needs to understand code quality standards
- After prototyping, when deciding which code to promote to production
- When transitioning from prototype to production-quality codebase
Problems this solves:
- Frame rate drops caused by per-frame allocations nobody noticed
- Physics that behave differently at 30fps vs 60fps vs 144fps
- State machines that enter impossible states under edge conditions
- Leaked resources on scene transitions causing gradual memory growth
- Hardcoded gameplay values that require recompilation to tune
- Circular dependencies that make systems impossible to test in isolation
- Raw input handling scattered through gameplay code instead of abstracted
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.
- 1mo ago First seen · 528 lines · 96 tokens per session scan A 85a260d12f1f
game-code-review is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (45 stars, last pushed 6mo ago), licensed MIT. It adds 96 tokens to every session and 5,116 once invoked, about $0.0004 per session on Opus 5.5. 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
roblox-code-maintenance-refactor
Maintain and refactor Roblox Luau code safely. Use for technical debt, dead code removal, module boundaries, naming cleanup, duplicate logic, dependency review, regression prevention, and long-term codebase health.
refactor
Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.
pre-publish-review
Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…
work-with-pr
Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…
remove-ai-slops
Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.