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/quantum3-labs/arbuilder/claude-mdgit clone --depth 1 https://github.com/Quantum3-Labs/ARBuilderWrote 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/quantum3-labs/arbuilder/claude-md)<a href="https://agentmods.dev/instructions/quantum3-labs/arbuilder/claude-md"><img src="https://agentmods.dev/badge/instructions/quantum3-labs/arbuilder/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 | $0.05543 | $0.05543 |
| Opus 5 | $0.02772 | $0.02772 |
| Sonnet 5 | $0.01109 | $0.01109 |
| Haiku 4.5 | $0.00554 | $0.00554 |
Grade A, and why
ARBuilder 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 3d 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 — 479 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
ARBuilder is an AI-powered development assistant for the Arbitrum ecosystem. It uses RAG (Retrieval-Augmented Generation) to provide context-aware code generation for:
- Stylus smart contracts (Rust/WASM)
- Arbitrum SDK bridging (TypeScript)
- Cross-chain messaging (L1 ↔ L2 ↔ L3)
- Full-stack dApps (contracts + backend + frontend + indexer)
- Orbit chain deployment (@arbitrum/orbit-sdk)
Repository Structure
ArbBuilder/
├── src/
│ ├── mcp/ # MCP server for IDE integration
│ │ ├── server.py # Main MCP server
│ │ ├── tools/ # 19 MCP tools (M1: 6, M2: 3, M3: 5, M4: 5)
│ │ ├── resources/ # Static knowledge (11 resources)
│ │ └── prompts/ # Workflow templates
│ ├── embeddings/ # Vector DB and retrieval
│ │ ├── vectordb.py # ChromaDB wrapper with hybrid BM25+vector search
│ │ └── reranker.py # BM25 + LLM reranking
│ ├── templates/ # Code generation templates
│ │ ├── stylus_templates.py # M1: Stylus contracts
│ │ ├── backend_templates.py # M3: NestJS/Express (ABI placeholder support)
│ │ ├── frontend_templates.py # M3: Next.js + wagmi (ABI placeholder support)
│ │ ├── indexer_templates.py # M3: The Graph subgraphs
│ │ ├── oracle_templates.py # M3: Chainlink integrations
│ │ └── orbit_templates.py # M4: Orbit chain deployment (@arbitrum/orbit-sdk)
│ ├── utils/ # Shared utilities
│ │ ├── version_manager.py # SDK version management
│ │ ├── env_config.py # Centralized env var configuration
│ │ ├── abi_extractor.py # Stylus ABI extraction from Rust code
│ │ └── compiler_verifier.py # Docker-based cargo check verification
│ └── preprocessing/ # Text chunking and cleaning
├── scraper/ # Data collection (web + GitHub)
├── data/
│ ├── raw/ # Scraped docs and repos
│ ├── processed/ # Pre-processed chunks
│ └── chroma_db/ # Vector database (local)
├── tests/ # Test suites
├── docs/ # Documentation
└── scripts/ # Utility scripts
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.
- 3d ago First seen · 479 lines · 5,543 tokens per session scan A bf0d72537b00
ARBuilder CLAUDE.md is an instructions file published in the GitHub repository Quantum3-Labs/ARBuilder (24 stars, last pushed 3mo ago), licensed MIT. It adds 5,543 tokens to every session, about $0.0277 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 2026-08-30.
Other instructions, from other repositories
shep AGENTS.md
AGENTS.md instructions for shep-ai/shep, covering agents.md, project, spec workflow, commands and architecture.
shep CLAUDE.md
Claude Code instructions for shep-ai/shep, covering claude.md, project, spec workflow, commands and architecture.
infura-mcp-server AGENTS.md
Instructions for Qbandev/infura-mcp-server, covering agents.md, tool categories, account queries (3 tools), block queries (7 tools) and transaction queries (6 tools).
drpc-agent-skills GEMINI.md
Gemini CLI instructions for drpcorg/drpc-agent-skills: @./skills/drpc-rpc/SKILL.md @./skills/drpc-rpc/setup.md @./skills/drpc-rpc/direct-http.md @./skills/drpc-rpc/tools-reference.md @./skills/drpc-rpc/recipes-simple.md @./skills/drpc-rpc/recipes-crosschain.md @./skills/drpc-rpc/recipes-defi-basics.md…
cadence-rules AGENTS.md
AGENTS.md instructions for onflow/cadence-rules, covering agents.md, repository layout, rules/cadence/ — cadence language rules, rules/workflows/ — project setup and development lifecycle and rules/defi-actions/ — defiactions composition patterns.
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).