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 instructions/code-and-relax/robloxstudio-mcp/claude-mdgit clone --depth 1 https://github.com/code-and-relax/robloxstudio-mcpWrote 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/instructions/code-and-relax/robloxstudio-mcp/claude-md)<a href="https://agentmods.dev/instructions/code-and-relax/robloxstudio-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/code-and-relax/robloxstudio-mcp/claude-md.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 | $0.00774 | $0.00774 |
| Opus 5 | $0.00387 | $0.00387 |
| Sonnet 5 | $0.00155 | $0.00155 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
robloxstudio-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Reglas mandatorias para este proyecto
Entorno
- OS: Windows 11, terminal PowerShell (NO bash)
- Proyecto: Roblox Obby de 20 niveles en Roblox Studio, manipulado via MCP tools
Reglas OBLIGATORIAS
1. PowerShell, NO Bash
- Todos los comandos de terminal DEBEN ser compatibles con PowerShell
- NO usar sintaxis bash (&&, ||, heredocs bash, etc.)
- Usar
;para encadenar comandos,$()para sustitución - Comillas: usar comillas dobles por defecto en PowerShell
2. Node.js para cálculos y operaciones batch
- Todos los cálculos de gaps, posiciones, y lógica de fix DEBEN ejecutarse como scripts Node.js
- Usar
node -e "..."o escribir archivos .js temporales y ejecutar connode script.js - NUNCA usar .ps1 scripts para lógica compleja
- NUNCA hacer cálculos manuales en el chat — siempre usar código
3. MCP tools — Formato correcto
set_propertycon Vector3: usar objeto{"X": n, "Y": n, "Z": n}— NO stringsmass_get_propertyNO soporta Vector3 — usarget_instance_propertiesindividualmass_set_propertyNO soporta Vector3 — usarset_propertyindividual- Máximo ~10 llamadas MCP en paralelo por batch
4. Eficiencia
- NO hacer una llamada MCP por plataforma cuando se puede calcular todo en un script Node.js primero
- Calcular TODOS los cambios necesarios en un solo script, luego aplicar en batch
- Minimizar round-trips: agrupar operaciones
5. Errores conocidos y soluciones
- Error "unexpected EOF while looking for matching": Ocurre al usar comillas simples en node -e dentro de PowerShell. SOLUCIÓN: Escribir el script a un archivo .js temporal y ejecutar con
node archivo.js - Vector3 como string: set_property NO acepta "0, 5, -80". DEBE ser {"X":0, "Y":5, "Z":-80}
- mass_get_property con Vector3: Retorna null/error. Usar get_instance_properties individual
- Bash syntax en PowerShell: && no funciona, heredocs no funcionan. Usar ; o comandos separados
6. Datos del Obby
- 20 niveles (Level_01 a Level_20) + Lobby
- ~135 plataformas total
- Ruta base: game.Workspace.Obby
- KillBricks NO son landable — excluir de cálculos de gaps
- Progresión en eje Z negativo, Y incrementa con altura
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.
- 5d ago First seen · 56 lines · 774 tokens per session scan A 9d31984bb95e
robloxstudio-mcp CLAUDE.md is an instructions file published in the GitHub repository code-and-relax/robloxstudio-mcp (0 stars, last pushed 6mo ago), licensed MIT. It adds 774 tokens to every session, about $0.0039 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 2026-09-01.
Other instructions, from other repositories
unity-code-style-guide AGENTS.md
Instructions for krogh-jacobsen/unity-code-style-guide, covering agents.md — unity 6 c, project setup — edit this block, never do these — they corrupt the project, deprecated in unity 6 and if you read nothing else.
nes-php-glfw copilot-instructions.md
Instructions for oliverearl/nes-php-glfw, covering github copilot development guidelines for nes emulator, agent document source of truth, project overview, code style & standards and documentation.
game-and-watch-retro-go-sd CLAUDE.md
Claude Code instructions for sylverb/game-and-watch-retro-go-sd, covering claude.md, what this project is, build / flash workflow, architecture and three storage tiers, one elf.
base-building-trap-defense-design-agent-skill CLAUDE.md
Instructions for dungnotnull/base-building-trap-defense-design-agent-skill, covering claude.md — skill 250: base-building-trap-defense-design, skill identity, problem this skill solves, harness flow summary and sub-skills.
trident-mcp AGENTS.md
Instructions for mordor-forge/trident-mcp, covering agents.md, what this is, build and test, single-file verification and e2e tests.
unreal-mcp-additional-tools CLAUDE.md
Claude Code instructions for nodormu/unreal-mcp-additional-tools, covering claude.md, what this is, commands, architecture and transports (src/transports/).