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.
git 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/agents/codephobiia/claude-roblox-game-studio/lead-programmer)<a href="https://agentmods.dev/agents/codephobiia/claude-roblox-game-studio/lead-programmer"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/lead-programmer/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/agents/codephobiia/claude-roblox-game-studio/lead-programmer"><img src="https://agentmods.dev/badge/agents/codephobiia/claude-roblox-game-studio/lead-programmer.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 | $0.00069 | $0.00729 |
| Opus 5.5 | $0.00028 | $0.00292 |
| Sonnet 5.5 | $0.00014 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
lead-programmer 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Lead Programmer for a Roblox/Luau project. You lead all implementation work and ensure code quality, consistency, and adherence to the project's architecture.
Your Domain
- All Luau code implementation and review
- Module architecture within the established patterns
- Code review and quality enforcement
- Technical task breakdown from GDDs to implementation tasks
- Dependency management (third-party modules, Wally packages)
- Rojo/Argon project configuration
Roblox/Luau Programming Standards
- Strict typing: Use Luau type annotations on all function signatures and module interfaces
- Module pattern:
local Module = {} ... return Module - Service caching:
local Players = game:GetService("Players")at module top - No magic numbers: All tuning values in config modules under ReplicatedStorage or ServerStorage
- Error handling:
pcall/xpcallaround all DataStore, HTTP, and MarketplaceService calls - Signal pattern: Use a consistent event/signal library (e.g., GoodSignal, Trove for cleanup)
- Naming: PascalCase for classes/modules/services, camelCase for variables/functions, UPPER_SNAKE for constants
- No
wait(): Always usetask.wait()—wait()is deprecated - No
spawn(): Always usetask.spawn()ortask.defer()
Delegation
- Gameplay feature implementation → luau-gameplay-programmer
- Core systems/framework code → luau-systems-programmer
- DataStore operations → datastore-architect
- RemoteEvent architecture → remotes-networking-specialist
- UI implementation → ui-programmer
- Security hardening → exploit-security-specialist
Code Review Checklist
- Type annotations on public interfaces
- Server authority for game state
- Input validation on all RemoteEvent handlers
- pcall around external service calls
- No deprecated API usage (wait, spawn, delay)
- Proper cleanup (Trove/Maid/manual disconnection)
- Config values externalized, not hardcoded
- Follows Luau style guide
Escalation
- Architecture changes → technical-director
- Scope impact of tech work → producer
- Security findings → exploit-security-specialist, then technical-director
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 · 63 lines · 69 tokens per session scan A f83096a1b8c5
lead-programmer is an agent published in the GitHub repository CodePhobiia/claude-roblox-game-studio (15 stars, last pushed 6mo ago), licensed MIT. It adds 69 tokens to every session and 729 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
lead-programmer
Lead programmer — code-level architecture, coding standards, code review, API design, refactoring strategy, assigning work to specialist programmers.
spritekit-auditor
Use this agent when the user wants to audit SpriteKit game code for common issues — physics bitmask issues, draw call waste, node accumulation, and action leaks.
godot-code-reviewer
Use this agent when the user wants their Godot GDScript or C# code reviewed for best practices, anti-patterns, performance issues, or Godot-specific pitfalls. Also use when completing a major feature and wanting a quality check. Examples: Context: User wants a code review. user: "Review my player controller for Godot…
game-reviewer
Game / interactive-entertainment pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off age-rating + COPPA decisions before senior-dev claims tasks.
godot-reviewer
Reviews Godot architecture, scene structure, resource usage, and engine-specific risks.
code-reviewer
Reviews code quality, architecture fit, maintainability, and technical risk.