infra CLAUDE.md

Repository instructions for AI coding agents working in the E2B infrastructure codebase. They cover the project overview, development commands, setup, and switching between production, staging, and development environments.

In plain words
What is it for?
Use them when setting up local development, switching environments, authenticating with Google Cloud, initializing Terraform, or changing E2B infrastructure.
Why use it?
They provide the background and repeatable setup steps needed to work in this infrastructure repository without guessing how its services and environments fit together.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/e2b-dev/infra/claude-md
Clone the repo
git clone --depth 1 https://github.com/e2b-dev/infra
Per session 2,503 This file is loaded in full into every session.
When invoked 2,503 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02503 $0.02503
Opus 5 $0.01252 $0.01252
Sonnet 5 $0.00501 $0.00501
Haiku 4.5 $0.00250 $0.00250

Measured 2d ago against content hash 47a5db40411b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

infra 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 2d 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.

CLAUDE.md · 298 lines

How it starts

The opening of the file, as written. The whole thing — 298 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

E2B Infrastructure is the backend infrastructure powering E2B (e2b.dev), an open-source cloud platform for AI code interpreting. It provides sandboxed execution environments using Firecracker microVMs, deployed on GCP using Terraform and Nomad.

Start with docs/ARCHITECTURE.md — it explains what each service does, how services interact (with diagrams of the core flows: sandbox creation, traffic routing, pause/resume, template builds), and the deployment topology. Reading it first is the fastest way to understand this repository.

Keep docs/ARCHITECTURE.md updated: if your change alters anything it describes (service responsibilities, ports, protocols, data stores, flows, deployment topology), update the document in the same change.

Common Development Commands

Setup & Environment

# Switch between environments (prod, staging, dev)
make switch-env ENV=staging

# Setup GCP authentication
make login-gcloud

# Initialize Terraform
make init

# Setup local development stack (PostgreSQL, Redis, ClickHouse, monitoring)
make local-infra

Building & Testing

# Run all unit tests across packages
make test

# Run integration tests
make test-integration

# Build specific package
make build/api
make build/orchestrator

# Generate code (proto, SQL, OpenAPI)
make generate

# Format and lint code
make fmt
make lint

# Regenerate mocks
make generate-mocks

# Tidy go dependencies
make tidy

Running Services Locally

# From packages/api/
make run-local          # Run API server on :3000
make dev                # Run with air (hot reload)

# From packages/orchestrator/
make run-local          # Run orchestrator
make run-debug          # Run with race detector

Package-Specific Commands

# API: Generate OpenAPI code
cd packages/api && make generate

# Orchestrator: Generate proto + OpenAPI
cd packages/orchestrator && make generate

# DB: Run migrations
make migrate

# Run single test
cd packages/<package> && go test -v -run TestName ./path/to/package

Read the full file on GitHub · 298 lines

Changes

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.

  1. 2d ago First seen · 298 lines · 2,503 tokens per session scan A 47a5db40411b

Subscribe to this mod's changes

infra CLAUDE.md is an instructions file published in the GitHub repository e2b-dev/infra (1,350 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,503 tokens to every session, about $0.0125 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.