What is aura-llm-gateway CLAUDE.md?

Un fichier de consignes pour un projet Rust qui sert de passerelle entre plusieurs fournisseurs de modèles d'IA. Il fournit une interface commune, du routage, un suivi des coûts et de l'observabilité, c'est-à-dire des informations sur le fonctionnement du service.

Il aide à travailler sur les types partagés, le proxy web, le routage des fournisseurs, la compression des prompts, la base PostgreSQL, Redis et les journaux. Le projet utilise notamment Rust, Axum, Tokio, SQLx et reqwest.

Il donne aux contributeurs une vue d'ensemble du projet, de ses technologies et de l'emplacement des principaux composants. Cela réduit le temps nécessaire pour comprendre où intervenir.

How UmaiTech/aura-llm-gateway configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to UmaiTech/aura-llm-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/UmaiTech/aura-llm-gateway/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/UmaiTech/aura-llm-gateway

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/umaitech/aura-llm-gateway/claude-md/github.svg)](https://agentmods.dev/instructions/umaitech/aura-llm-gateway/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/umaitech/aura-llm-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/umaitech/aura-llm-gateway/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/umaitech/aura-llm-gateway/claude-md"><img src="https://agentmods.dev/badge/instructions/umaitech/aura-llm-gateway/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,701 This file is loaded in full into every session.

When invoked 5,701 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 98% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.05701	$0.05701
Opus 5.5	$0.02280	$0.02280
Sonnet 5.5	$0.01140	$0.01140
Haiku 4.5	$0.00570	$0.00570

Measured 14d ago against content hash 98afdd5a5a5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aura-llm-gateway 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 14d 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.

Origin

This is a copy

98% identical to aura-llm-gateway AGENTS.md — 40 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.

CLAUDE.md · 464 lines

How it starts

The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aura LLM Gateway

Project Overview

Rust-based LLM proxy implementing the Open Responses API specification for agentic workflows. Provides a unified interface to multiple LLM providers (OpenAI, Anthropic, Google) with load balancing, cost tracking, and observability.

Tech Stack

Language: Rust (2021 edition)
Web Framework: Axum
Database: PostgreSQL (SQLx), Redis
Async Runtime: Tokio
Serialization: Serde
Error Handling: thiserror, anyhow
Logging: tracing
HTTP Client: reqwest

Project Structure

/crates/
  aura-types/     # Shared type definitions (Open Responses API types)
    src/
      compression.rs   # Compression config types
      consistency.rs   # Response consistency types
      validation.rs    # Response validation types
  aura-core/      # Core business logic (providers, routing, caching)
    src/
      compression/     # Prompt compression (TOON, YAML, AISP, JSON)
      provider/        # LLM providers (OpenAI, Anthropic, Google)
      router/          # Smart routing with health tracking
  aura-proxy/     # Main server binary (Axum routes, middleware)
  aura-db/        # Database models and queries (SQLx)
/apps/
  chat/           # React chat playground (Vite + React 18)
  landing/        # Marketing landing page (Vite + React, MDX docs)
/docs/            # Documentation
  api/            # API documentation (Markdown)
/migrations/      # SQLx database migrations
/sdks/
  python/         # Python SDK (aura-llm on PyPI)

Development Commands

# Build
cargo build                    # Build all crates
cargo build --release          # Build optimized binary

# Test
cargo test                     # Run all tests
cargo test -p aura-core        # Test specific crate
cargo test -- --nocapture      # Show println output

# Run
cargo run -p aura-proxy        # Run the proxy server
RUST_LOG=debug cargo run -p aura-proxy  # With debug logging

# Lint & Format
cargo clippy                   # Lint all crates
cargo clippy --fix             # Auto-fix lint issues
cargo fmt                      # Format code
cargo fmt -- --check           # Check formatting

# Database (requires sqlx-cli)
sqlx migrate run               # Run migrations
sqlx migrate add <name>        # Create new migration

# Docker
docker-compose up -d           # Start local stack
docker-compose logs -f         # Follow logs

# Frontend Apps
cd apps/chat && npm run dev    # Run chat playground (port 3000)
cd apps/landing && npm run dev # Run landing page (port 3001)
cd apps/chat && npm run build  # Build chat app for production

Read the full file on GitHub · 464 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.

14d ago Changed · +8 lines · +581 tokens per session 98afdd5a5a5e
2mo ago First seen · 456 lines · 5,120 tokens per session scan A ae3bad59f378

Subscribe to this mod's changes

aura-llm-gateway CLAUDE.md is an instructions file published in the GitHub repository UmaiTech/aura-llm-gateway (12 stars, last pushed 14d ago), licensed MIT. It adds 5,701 tokens to every session, about $0.0228 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 98% identical to aura-llm-gateway AGENTS.md, differing in 40 lines, and is treated as a copy.

Backend and APIs LLM agentic ai anthropic axum gateway

aura-llm-gateway CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aura-llm-gateway CLAUDE.mdUmaiTech/aura-llm-gateway	Instructions file	12	14d ago	MIT	A	5,701	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

aura-llm-gateway: Instructions file for Claude Code