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 CodePhobiia/claude-roblox-game-studio --skill startgit clone --depth 1 https://github.com/CodePhobiia/claude-roblox-game-studioWrote 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/codephobiia/claude-roblox-game-studio/start)<a href="https://agentmods.dev/skills/codephobiia/claude-roblox-game-studio/start"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/start/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/codephobiia/claude-roblox-game-studio/start"><img src="https://agentmods.dev/badge/skills/codephobiia/claude-roblox-game-studio/start.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 | $0.00040 | $0.01985 |
| Opus 5.5 | $0.00016 | $0.00794 |
| Sonnet 5.5 | $0.00008 | $0.00397 |
| Haiku 4.5 | $0.00004 | $0.00198 |
Grade A, and why
start 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 2mo 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/start — Project Onboarding
Welcome the user and determine their starting point by asking:
"Where are you with this project?"
- No idea — I don't even have a game concept yet
- Vague concept — I have a rough idea but nothing documented
- Clear design — I have a GDD or design docs ready
- Existing code — I have a Roblox project with code already
Based on their answer:
If "No idea":
- Run
/brainstormto explore game ideas - Guide through genre selection, target audience, core loop definition
- Help define creative pillars (3-5 words each that describe the experience)
- Draft a 1-page game concept document
- Proceed to
/gddfor the master GDD
If "Vague concept":
- Ask them to describe their idea in 2-3 sentences
- Ask: What Roblox games inspire this? What's the core loop?
- Help crystallize: genre, setting, core mechanic, target audience
- Define creative pillars
- Proceed to
/gdd
If "Clear design":
- Ask them to share or describe their existing design docs
- Review for completeness against GDD standards
- Run
/project-stage-detectto assess readiness - Identify gaps and create a plan to fill them
- Set up the project structure if not already done
If "Existing code":
- Ask them to describe the project and share the codebase location
- Run
/reverse-documentto generate docs from existing code - Run
/project-stage-detectto assess current stage - Identify technical debt with
/tech-debt - Create a plan for what's next
Team Size Preset
After the starting-point question, ask:
"What's your team size?"
- Solo — just me. Streamlined review, fewer agent interactions.
- Small team (2-5) — lean review, key specialists involved.
- Studio (5+) — full review pipeline, all agents active.
Based on the answer, set review_mode automatically:
- Solo ->
solo - Small team ->
lean - Studio ->
full
Genre Preset (optional)
Ask:
"What genre?" (Tell the user they can skip this if they don't know yet.)
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.
- 2mo ago First seen · 203 lines · 40 tokens per session scan A 56e0ca19d944
start is a skill published in the GitHub repository CodePhobiia/claude-roblox-game-studio (19 stars, last pushed 7mo ago), licensed MIT. It adds 40 tokens to every session and 1,985 once invoked, about $0.0002 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 2026-09-03.
start compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| startCodePhobiia/claude-roblox-game-studio | Skill | 19 | 7mo ago | MIT | A | 40 | Claude Code |
| playtest-reportDonchitos/Claude-Code-Game-Studios | Skill | 39k | 5d ago | MIT | A | 20 | Claude Code |
| godot-signals-groupsgamedev-skills/awesome-gamedev-agent-skills | Skill | 8.9k | 2d ago | Apache-2.0 | A | 93 | Claude Code |
| texture-workflowarjun988/blender-skills | Skill | 2.8k | 8d ago | MIT | A | 41 | Claude Code |
| scenario-unreal-gameplayscenario-labs/skills | Skill | 3.8k | yesterday | MIT | A | 121 | Claude Code |
| motionOpenDCAI/GameFactory-3A | Skill | 1.0k | 3d ago | Apache-2.0 | A | 0 | Claude Code, Codex |
| gamedev-shadersericrisco/rsc-harness | Skill | 606 | yesterday | MIT | A | 102 | Claude Code, Codex |