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 vasilyu1983/AI-Agents-public --skill gamedev-robloxgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/gamedev-roblox)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/gamedev-roblox"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/gamedev-roblox/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/vasilyu1983/ai-agents-public/gamedev-roblox"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/gamedev-roblox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 40 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00031 | $0.03761 |
| Opus 5 | $0.00015 | $0.01880 |
| Sonnet 5 | $0.00006 | $0.00752 |
| Haiku 4.5 | $0.00003 | $0.00376 |
Grade A, and why
gamedev-roblox 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Roblox World Creation
Use this skill to take a Roblox experience from empty Studio place to a published, retainable world using the engine, language, and platform reality of July 2026. It covers the durable build spine (greybox → first playable → detail → ship) and fences the volatile platform layer (rates, limits, renamed APIs) so you teach what is true today, not what was true in 2023 — or in May 2026 (the RFY discovery algorithm, DataStore budget model, and 2D UGC publishing rules all materially changed since then; see the dated corrections in references/discovery-economy-policy.md and references/luau-and-architecture.md).
This is a software/game-development domain skill. It is self-contained: pick the stage you are in, load the one reference for that stage, do the work, verify volatile claims before quoting them.
Quick Reference
| Stage | Read or Run | Durable default (Jul 2026) |
|---|---|---|
| Setup & toolchain | references/setup-and-toolchain.md |
Studio + Rojo + Rokit + Wally for git-native teams; Script Sync (Full Release since Jun 2026, Team-Create compatible) if you need Team Create; default.project.json defines the DataModel tree |
| Language & architecture | references/luau-and-architecture.md |
--!strict Luau; task.wait/spawn/defer never wait()/spawn(); server-authoritative; RemoteEvent + UnreliableRemoteEvent for high-frequency; ProfileStore for player data |
| Build the world | references/world-building.md |
Greybox in Parts first; 1 stud ≈ 0.28 m; StreamingEnabled = true; Unified Lighting LightingStyle = Realistic + PrioritizeLightingQuality (the old Technology enum is deprecated) |
| Performance & traps | references/performance-and-traps.md |
Anchor static parts; transparency 0 or 1 only; disconnect every connection; UpdateAsync + session lock + BindToClose; WaitForChild in LocalScripts |
| Discovery, economy, policy | references/discovery-economy-policy.md |
Design for RFY's 28-day, 3-phase retention model (Day 1 / Day 2–7 / Day 8–28; rewritten Jun 2026 — the old 7-day qPTR model is superseded); complete the maturity questionnaire; design sinks for every source; never trust the client for economy |
| AI-assisted creation | references/setup-and-toolchain.md#ai-assisted-creation |
Studio Assistant (planning mode), Material Generator (GA), Code Assist, Studio MCP server for external LLMs — real and shipping; Texture Generator still Beta |
What ships with it
9 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.
- agents/openai.yaml 342 B
- data/sources.json 17 KB
- learnings.consolidated.md 1.1 KB
- learnings.md 386 B
- references/discovery-economy-policy.md 18 KB
- references/luau-and-architecture.md 15 KB
- references/performance-and-traps.md 8.5 KB
- references/setup-and-toolchain.md 6.4 KB
- references/world-building.md 7.2 KB
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 · 133 lines · 31 tokens per session scan A ac2e6b0821b0
gamedev-roblox is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 31 tokens to every session and 3,761 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
procedural-generation
Procedural generation patterns — Perlin/Simplex noise, BSP dungeon generation, random walk, loot tables with weighted random, wave function collapse basics, seed-based reproducibility.
dialogue-system
Dialogue tree patterns — ScriptableObject graph, node types (text, choice, condition, event), typewriter effect, localization-ready. Load when implementing NPC conversations.
inventory-system
Inventory, equipment, and crafting patterns — ScriptableObject item definitions, slot-based inventory, equipment system, crafting recipes, UI binding. Load when implementing item management.
save-system
Save/load patterns — ISaveable interface, JSON serialization, save file management, scene persistence, cloud sync prep. Load when implementing save functionality.
state-machine
Generic state machine patterns — IState interface, StateMachine , game state management (menu/gameplay/pause), enemy AI states, hierarchical FSM. Load when implementing state-driven behavior.
character-controller
2D and 3D character controller patterns — coyote time, input buffering, variable jump, wall slide/jump, dash, slopes, stairs, camera-relative movement. Load when implementing player movement.