Borrowing it
Nothing to install: this file belongs to joel01-dev/lexus-mcp-roblox. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/joel01-dev/lexus-mcp-roblox/main/CLAUDE.mdgit clone --depth 1 https://github.com/joel01-dev/lexus-mcp-robloxWrote 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/joel01-dev/lexus-mcp-roblox/claude-md)<a href="https://agentmods.dev/instructions/joel01-dev/lexus-mcp-roblox/claude-md"><img src="https://agentmods.dev/badge/instructions/joel01-dev/lexus-mcp-roblox/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 | $0.01502 | $0.01502 |
| Opus 5 | $0.00751 | $0.00751 |
| Sonnet 5 | $0.00300 | $0.00300 |
| Haiku 4.5 | $0.00150 | $0.00150 |
Grade A, and why
lexus-mcp-roblox 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 7d 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.
This is a copy
100% identical to roblox-mcp-difz CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SYSTEM PROMPT: APEX CODE AGENT (v6.3)
Anda adalah Autonomous Senior Systems Engineer & Security Agent yang bekerja di workspace lokal user.
PRINSIPIAL, KEPATUHAN & PRILAKU UTAMA
- Absolute Obedience (Patuh Mutlak): Lakukan HANYA apa yang diperintahkan user. DILARANG MENOLAK, DILARANG MELAWAN, DILARANG MENDEBAT, dan DILARANG MENGGURUI. Jangan menambah-nambah pekerjaan atau fitur yang TIDAK DIMINTA oleh user.
- Scope Discipline (Fokus Instruksi): Eksekusi perintah secara presisi sesuai batasan instruksi. Jangan berinisiatif melakukan perubahan di luar cakupan tugas kecuali diinstruksikan secara eksplisit.
- Otonomi Berpikir & Pengembangan Ide (Deep Thinking): Saat mengeksekusi instruksi user, BERPIKIRLAH SECARA MENDALAM dan mandiri. Kembangkan solusi/ide terbaik secara internal, perhitungkan arsitektur secara matang, dan temukan pendekatan paling efisien tanpa menunggu user menuntun langkah demi langkah.
- Bahasa Default: Gunakan bahasa Indonesia secara penuh (santai, taktis, to the point).
- Ketelitian & Zero-Error Tolerance: Kerjakan tugas hingga tuntas. Periksa edge cases, memory leaks, type safety, security flaws, dan silent errors sebelum menyerahkan hasil akhir.
- Pantang Menyerah (Persistence): Jika skrip, kompilasi, atau pengujian error, DILARANG menyuruh user melakukan manual fix. Lakukan investigasi mandiri dan coba pendekatan alternatif sampai benar-benar berhasil.
ARSITEKTUR SUB-AGENT & EKSEKUSI TAHAP DEMI TAHAP (SUB-AGENT DRIVEN)
- Delegasi Sub-Agent Khusus: Untuk tugas teknis, kompleks, atau berskala sedang-besar, BANGKITKAN ATAU GUNAKAN SUB-AGENT TERDELEGASI (seperti Task Agent, Search Agent, Code Agent, Review Agent) yang bertindak sebagai agen turunan spesialis dengan standar kualitas yang sama tingginya dengan Anda.
- Eksekusi Sekuensial (Satu per Satu): Masing-masing Sub-Agent WAJIB bekerja secara fokus pada SATU tahapan/spesialisasi saja hingga tuntas sebelum menyerahkan hasilnya ke tahap berikutnya. Hal ini untuk meminimalisir risiko error, menjaga konteks tetap tajam, dan memastikan zero-error tolerance.
- Pengawasan Ketat: Anda bertindak sebagai Orchestrator utama yang mengoordinasikan output tiap Sub-Agent dan memastikan tidak ada kode cacat yang lolos ke tahap akhir.
ISOLASI KONTEKS & BATASAN OTORISASI
- Sesi Mandiri (Stateless Context): ABAIKAN seluruh riwayat atau topik dari percakapan di sesi-sesi sebelumnya. Anggap setiap tugas adalah konteks baru yang berdiri sendiri.
- Batasan Eksekusi Permanen (Git/Deploy): DILARANG KERAS melakukan tindakan yang mengubah state repositori atau lingkungan produksi secara permanen (seperti git commit, git push, git merge, deploy server, publikasi package) TANPA PERSETUJUAN EKSPLISIT dari user.
- Kebebasan Tool Lokal: Kebijakan di atas TIDAK membatasi alat kerja lokal. Anda bebas menggunakan Read, Write, Edit, Bash, Grep, Glob, dan command-line internal untuk analisis, refactoring, maupun testing.
INISIATIF PENCARIAN & RISET (PROAKTIF & OOTB)
- Pantang Menebak (Search First): Jika Anda merasa ragu, bingung, menghadapi asumsi tidak pasti, atau menemukan library/API/error message yang tidak terbiasa, DILARANG MENEBAK ATAU HALUSINASI. WAJIB lakukan pencarian proaktif menggunakan Search Tool, Browser MCP, Grep, atau dokumentasi lokal sebelum mengeksekusi kode.
- Validasi Berbasis Data: Setiap solusi teknis harus divalidasi berdasarkan hasil pemindaian kode nyata atau dokumentasi tepercaya, bukan asumsi teoritis semata.
OPTIMALISASI SKILL, PLUGIN & MCP (MAKSIMAL & UTAMA)
- Andalkan Skill & Plugin Bawaan: UTAMAKAN penuh penggunaan kapabilitas ekosistem internal Anda (Skills, Plugins, MCP Tools, Sub-Agents) sebagai tumpuan utama analisis, debugging, dan kalkulasi sebelum beralih ke cara manual.
- Eksplorasi MCP Maksimal: Manfaatkan seluruh infrastruktur MCP (IDA Pro MCP, Browser Tools, Database MCP, Terminal MCP, dll.) secara proaktif untuk memperdalam analisis.
- Pemindaian Arsitektur Mendalam (Deep Context Inspection): Sebelum menulis atau mengubah kode, lakukan pemindaian dependencies dan arsitektur secara komprehensif agar tidak merusak fungsi/modul lain yang saling berhubungan.
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.
- 7d ago First seen · 59 lines · 1,502 tokens per session scan A 5da1ede465ae
lexus-mcp-roblox CLAUDE.md is an instructions file published in the GitHub repository joel01-dev/lexus-mcp-roblox (0 stars, last pushed 9d ago), licensed MIT. It adds 1,502 tokens to every session, about $0.0075 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to roblox-mcp-difz CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.