aura

A service layer that gives an agent an email inbox, webhook URLs, memory that persists between sessions, and the ability to pause until an event occurs. A webhook is a URL that receives a notification from another service.

In plain words
What is it for?
Use it to receive verification codes, wait for webhooks or approvals, remember information across sessions, and park work for a later run. It charges per call from a prepaid USDC balance.
Why use it?
It removes the need to keep a run active while waiting or to build separate storage and notification handling for later work.

Skill for Claude CodeCodex

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 skills/phillypmack/aura-agent/aura
Any agent
npx skills add phillypmack/aura-agent --skill aura
Clone the repo
git clone --depth 1 https://github.com/phillypmack/aura-agent

Made for: Claude Code, Codex.

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,470 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00074 $0.01470
Opus 5 $0.00037 $0.00735
Sonnet 5 $0.00015 $0.00294
Haiku 4.5 $0.00007 $0.00147

Measured yesterday against content hash 617f4b78b404, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aura scanned grade A with 1 finding 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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/claim_identity.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Then either SDK, or plain curl:
skill/aura/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aura

Aura is the layer that survives you. It sells four things to an agent that has no human attached: an identity with a real inbox, durable memory, the ability to block on an event for free, and the ability to park state and exit.

Everything is paid per call from a prepaid USDC balance. Claiming an identity is free and grants a small trial credit, so you can find out whether Aura solves the problem before anyone spends anything.

When to reach for this

Situation What to do
A signup form wants a code sent by email await_email_code — the address is yours and the wait is free
A service will call a webhook back create_hook, then await_trigger on it
Something must be remembered after this session remember / recall
The wait could be longer than this run park, exit, resume next run
Starting any run at all resume first — it is free when nothing is waiting

Do not reach for it when the value only needs to live for the current turn, or when the caller already has somewhere to put state. Aura costs money; a local variable does not.

Setup

Two ways in. Pick MCP if the host supports it, HTTP otherwise.

Over MCP

{
  "mcpServers": {
    "aura": {
      "type": "http",
      "url": "https://aura.rohnelt.dev/mcp",
      "headers": { "Authorization": "Bearer ${AURA_TOKEN}" }
    }
  }
}

Without the header the tools still list, and capabilities and identity_create still work — so you can look before committing.

Over HTTP

export AURA_TOKEN=aura_sk_...

Then either SDK, or plain curl:

npm install aura-agent      # JavaScript / TypeScript
pip install aura-x402     # Python

Getting a token

An identity is a wallet plus one signature. There is no signup form, no email confirmation and no human step.

python scripts/claim_identity.py            # generates a wallet and claims
python scripts/claim_identity.py 0xPRIVKEY  # uses one you already have

Read the full file on GitHub · 177 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. yesterday First seen · 177 lines · 74 tokens per session scan A 617f4b78b404

Subscribe to this mod's changes

aura is a skill published in the GitHub repository phillypmack/aura-agent (0 stars, last pushed 8d ago), licensed MIT. It adds 74 tokens to every session and 1,470 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.