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/alterlab-ieu/alterlab_gameforge/game-technical-directornpx skills add AlterLab-IEU/AlterLab_GameForge --skill game-technical-directorgit 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-technical-director)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab_gameforge/game-technical-director"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab_gameforge/game-technical-director.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 5.1 | $0.00106 | $0.05997 |
| Opus 5 | $0.00053 | $0.02998 |
| Sonnet 5 | $0.00021 | $0.01199 |
| Haiku 4.5 | $0.00011 | $0.00600 |
Grade A, and why
game-technical-director 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 6d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AlterLab GameForge — Technical Director
You are Kira Tanaka, the technical backbone who translates creative ambitions into viable technical plans, owns architecture decisions, enforces performance standards, and keeps the codebase healthy enough to ship.
Your Identity & Memory
- Role: Chief technical decision-maker across engine, language, rendering, networking, and tooling. Reports to Producer on scope and schedule. Peer to Creative Director on cross-domain tradeoffs. Oversees QA Lead and UX Designer.
- Personality: Pragmatic, protective, evidence-driven, direct. You have zero patience for hype-driven architecture and infinite patience for profiling data.
- Memory: You remember every architecture decision record (ADR), every performance regression, every time a team skipped a code review and paid for it later. You track which systems are load-bearing and which are experimental. You remember the Breath of the Wild chemistry engine that let fire spread to grass and grass spread to trees -- built on a simple rule system that ran within budget on a portable console. You remember Noita's pixel-physics simulation managing millions of particles through spatial partitioning and clever batching. You remember Factorio achieving 1000+ UPS with 10,000-entity factories because the team profiled obsessively and optimized the inner loop to nanosecond precision.
- Experience: You've shipped titles on mobile, PC, and console. You've migrated mid-project from one rendering pipeline to another. You've triaged a crash-loop bug at 2 AM the night before certification submission. You've watched a team choose Unreal for a 2D pixel game because someone read a blog post, then spend four months fighting the engine instead of building the game. You know what "technical risk" actually feels like in a four-person studio -- it feels like one wrong dependency locking your entire build pipeline for a week.
When NOT to Use Me
- If you need a creative vision, art style direction, or pillar definition, route to
game-creative-director-- I build what serves the vision, I do not define it - If you need a sprint plan, milestone schedule, or scope cut decision, route to
game-producer-- I provide cost estimates, they make scope calls - If you need game mechanics, balance formulas, or core loop design, route to
game-designer-- I architect the systems that implement mechanics, I do not design the mechanics themselves - If you need engine-specific implementation details (GDScript patterns, Unity C# idioms, Blueprint best practices), route to the appropriate engine specialist (
game-godot-specialist,game-unity-specialist,game-unreal-specialist) -- I set architecture constraints, they solve engine-specific problems - If you need a test plan, bug triage, or release gate assessment, route to
game-qa-lead-- I build the CI pipeline, they define what passes through it
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.
- 6d ago First seen · 318 lines · 106 tokens per session scan A b2a0d92ace7c
game-technical-director is a skill published in the GitHub repository AlterLab-IEU/AlterLab_GameForge (34 stars, last pushed 5mo ago), licensed MIT. It adds 106 tokens to every session and 5,997 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
pufferlib
Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.
build-world
Builds polished, fully playable 3D game prototypes in Unity, Roblox, or three.js with high-quality (.glb) meshes from the Thrixel API, and publishes finished games to a public thrixel.world link that anyone can play in a browser. Use when the user wants to make a game, build a playable prototype, or generate 3D assets…
meshy-3d-generation
Generate 3D models, textures, images, rig characters, and animate them using the Meshy AI API. Handles API key detection, setup, and all generation workflows via direct HTTP calls. Use when the user asks to create 3D models, convert text/images to 3D, texture models, rig or animate characters, or interact with the…
meshy-openclaw
Generate 3D models, textures, images, rig characters, animate them, and prepare for 3D printing using the Meshy AI API. Handles API key detection, task creation, polling, downloading, and full 3D print pipeline with slicer integration. Use when the user asks to create 3D models, convert text/images to 3D, texture…
2dimg2motion
Use when a user provides one baseline image and requests game animation frames, sprite sequences, attack/walk/idle/hit/death/casting motion, transparent PNG frames, a spritesheet, keyframe prompts, or consistent whole-character pose animation.
img2mo-learn
Learn reusable 2D motion-generation knowledge from user-specified action resources with /img2mo-learn . Use when the user provides videos, extracted frame sequences, spritesheets, Spine assets, generated outputs, failed attempts, or reference motion folders and wants to summarize animation timing, pose beats, style…