aura CLAUDE.md

aura CLAUDE.md is an instructions file for coding agents from mezmo/aura. It costs 5,043 tokens per session, scanned A, original, Apache-2.0.

Project instructions and documentation for AURA, a Rust system that combines configuration files with AI agents, tool connections, and retrieval pipelines.

In plain words
What is it for?
Building and starting AURA, choosing its configuration, running multi-agent workflows, and understanding known pending work.
Why use it?
They give a coding agent the project’s current state, setup commands, and rules for running its web server and command-line client.

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/mezmo/aura/claude-md
Clone the repo
git clone --depth 1 https://github.com/mezmo/aura

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.

agentmods badge for aura CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mezmo/aura/claude-md.svg)](https://agentmods.dev/instructions/mezmo/aura/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/mezmo/aura/claude-md"><img src="https://agentmods.dev/badge/instructions/mezmo/aura/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 5,043 This file is loaded in full into every session.
When invoked 5,043 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 $0.05043 $0.05043
Opus 5 $0.02521 $0.02521
Sonnet 5 $0.01009 $0.01009
Haiku 4.5 $0.00504 $0.00504

Measured 4d ago against content hash 4af8c07c9744, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aura 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 4d 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 · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Project Documentation

If CLAUDE.local.md exists in this directory, read it first — it contains current session state.

Overview

AURA is a TOML-based configuration system for composing Rig.rs AI agents with MCP tools and RAG pipelines.

Current Status: Production Ready

All major features complete:

  • Bounded streaming with custom aura events
  • Rig 0.28 upgrade with ProviderAgent architecture
  • Configurable MCP header forwarding (headers_from_request with static TOML fallback)
  • Request-scoped MCP progress and cancellation
  • Client disconnect detection with MCP notifications/cancelled
  • Multi-agent orchestration mode with coordinator/worker architecture and DAG execution

Pending: Upstream Rig PRs - StreamingPromptHook fix + Content-Type header fix


Quick Start

# Build
cargo build --release

# Start web server (default config.toml)
cargo run --bin aura -- webserver

# Start with orchestration config
CONFIG_PATH=configs/example-math-orchestration.toml AURA_CUSTOM_EVENTS=true cargo run --bin aura -- webserver

# Build and run CLI (HTTP mode — connects to a running `aura webserver`)
cargo run -p aura-cli -- --api-url http://localhost:8080

# Build and run CLI (standalone mode — no server needed, default when --api-url absent)
cargo run -p aura-cli -- --config configs/my-agent.toml

# Run integration tests (local, requires Docker)
make test-integration-local                        # base integration
make test-integration-orchestration-local          # orchestration integration
make test-integration-sre-orchestration-local      # SRE orchestration integration

Project Structure

aura/
├── crates/
│   ├── aura/                 # Core library (agent builder + orchestration)
│   ├── aura-cli/             # The `aura` binary: interactive client + `webserver` mode
│   ├── aura-config/          # TOML parsing and configuration
│   ├── aura-events/          # Shared SSE event types (lightweight, no agent deps)
│   ├── aura-web-server/      # OpenAI-compatible API + shared server entry point
│   └── aura-test-utils/      # Shared testing utilities
├── compose/                  # Docker Compose (integration + orchestration overlays)
├── configs/                  # Integration test and example configurations
├── deployment/               # Helm charts and K8s manifests
├── docs/                     # Architecture and protocol documentation
├── examples/                 # Example and reference configurations
└── .makefiles/               # Modular Make targets (rust, docker, node, aura)

Read the full file on GitHub · 262 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. 4d ago First seen · 262 lines · 5,043 tokens per session scan A 4af8c07c9744

Subscribe to this mod's changes

aura CLAUDE.md is an instructions file published in the GitHub repository mezmo/aura (284 stars, last pushed today), licensed Apache-2.0. It adds 5,043 tokens to every session, about $0.0252 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.