autonomy_service

autonomy_service is a command for Claude Code from valory-xyz/open-autonomy. It costs 0 tokens per session (2,792 once invoked), scanned A, original, Apache-2.0.

A command group for managing AI agents registered on the Autonolas Protocol, a blockchain-based system for publishing and operating agents. It can prepare transactions for supported blockchain networks.

In plain words
What is it for?
Managing registered agents, testing blockchain operations without sending them, choosing a supported network, and signing transactions.
Why use it?
It provides one interface for agent life-cycle operations across several networks and supports dry runs before transactions are sent. Transactions can be signed with a private-key file or hardware wallet.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

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 commands/valory-xyz/open-autonomy/autonomy_service
Clone the repo
git clone --depth 1 https://github.com/valory-xyz/open-autonomy

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.

agentmods badge for autonomy_service

README.md
[![agentmods](https://agentmods.dev/badge/commands/valory-xyz/open-autonomy/autonomy_service.svg)](https://agentmods.dev/commands/valory-xyz/open-autonomy/autonomy_service)
Your own site
<a href="https://agentmods.dev/commands/valory-xyz/open-autonomy/autonomy_service"><img src="https://agentmods.dev/badge/commands/valory-xyz/open-autonomy/autonomy_service.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,792 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.02792
Opus 5 $0.00000 $0.01396
Sonnet 5 $0.00000 $0.00558
Haiku 4.5 $0.00000 $0.00279

Measured 6d ago against content hash 4fa29cb08e31, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

autonomy_service 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 6d 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.

docs/advanced_reference/commands/autonomy_service.md · 382 lines

How it starts

The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tools to manage AI agents minted in the {{ autonolas_protocol }}.

This command group consists of a number of functionalities to manage the life cycle of AI agents that have been minted in the {{ autonolas_protocol }}.

!!! info

You can specify how you wish to sign the on-chain transactions produced by these commands: either with **a private key stored in a file**, or with a **hardware wallet**. In this latter case, ensure that you have configured properly the drivers for your hardware wallet.

Options

--dry-run : Perform a dry run for the transaction.

--use-celo : Use the Celo chain profile to interact with the Autonolas Protocol registry contracts.

--use-base : Use the Base chain profile to interact with the Autonolas Protocol registry contracts.

--use-optimism : Use the Optimism chain profile to interact with the Autonolas Protocol registry contracts.

--use-arbitrum-one : Use the Arbitrum One chain profile to interact with the Autonolas Protocol registry contracts.

--use-gnosis : Use the Gnosis chain profile to interact with the Autonolas Protocol registry contracts.

--use-polygon : Use the Polygon chain profile to interact with the Autonolas Protocol registry contracts.

--use-ethereum : Use the Ethereum chain profile to interact with the Autonolas Protocol registry contracts.

To use these chain profiles, you have to export an environment variable that defines the RPC endpoint in the format <CHAIN_NAME>_CHAIN_RPC. For example, if you want to use Ethereum (--use-ethereum), you have to export ETHEREUM_CHAIN_RPC.

--use-custom-chain : Use the custom-chain profile to interact with the Autonolas Protocol registry contracts. This profile requires that you define some parameters and contract addresses as environment variables (see also the {{ autonolas_protocol }} documentation for more information):

- `CUSTOM_CHAIN_RPC` : RPC endpoint for the custom chain.
- `CUSTOM_CHAIN_ID` : chain ID.
- `CUSTOM_COMPONENT_REGISTRY_ADDRESS`
- `CUSTOM_AGENT_REGISTRY_ADDRESS`
- `CUSTOM_REGISTRIES_MANAGER_ADDRESS`
- `CUSTOM_SERVICE_MANAGER_ADDRESS`
- `CUSTOM_SERVICE_REGISTRY_ADDRESS`
- `CUSTOM_GNOSIS_SAFE_PROXY_FACTORY_ADDRESS`<sup>&#8224;</sup>
- `CUSTOM_GNOSIS_SAFE_SAME_ADDRESS_MULTISIG_ADDRESS`<sup>&#8224;</sup>
- `CUSTOM_SAFE_MULTISIG_WITH_RECOVERY_MODULE_ADDRESS`<sup>&#8225;</sup>
- `CUSTOM_RECOVERY_MODULE_ADDRESS`<sup>&#8225;</sup>
- `CUSTOM_SERVICE_REGISTRY_TOKEN_UTILITY_ADDRESS`
- `CUSTOM_MULTISEND_ADDRESS`

!!! note
    For L2 chains you are only required to set

    - `CUSTOM_SERVICE_MANAGER_ADDRESS`
    - `CUSTOM_SERVICE_REGISTRY_ADDRESS`
    - `CUSTOM_GNOSIS_SAFE_PROXY_FACTORY_ADDRESS`<sup>&#8224;</sup>
    - `CUSTOM_GNOSIS_SAFE_SAME_ADDRESS_MULTISIG_ADDRESS`<sup>&#8224;</sup>
    - `CUSTOM_SAFE_MULTISIG_WITH_RECOVERY_MODULE_ADDRESS`<sup>&#8225;</sup>
    - `CUSTOM_RECOVERY_MODULE_ADDRESS`<sup>&#8225;</sup>
    - `CUSTOM_MULTISEND_ADDRESS`

<sup>&#8224;</sup> Required only if `--use-recovery` is not specified.

<sup>&#8225;</sup> Required only if `--use-recovery` is specified.

--use-local : Use the local chain profile to interact with the Autonolas Protocol registry contracts. This option requires that you have a local Hardhat node with the required contracts deployed.

!!! note

The chain profile flags (`--use-ethereum`, etc.) are mutually exclusive.

--use-recovery : Use a multisig with a recovery module when deploying or redeploying the AI agent. This module allows ownership of the AI agent multisig to be transferred to the AI agent owner if the agent instances have not done so. This functionality is only available during the Pre-Registration phase and is executed automatically when activating the AI agent. See notes † and ‡ above.

Read the full file on GitHub · 382 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. 6d ago First seen · 382 lines · 0 tokens per session scan A 4fa29cb08e31

Subscribe to this mod's changes

autonomy_service is a command published in the GitHub repository valory-xyz/open-autonomy (127 stars, last pushed 9d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,792 tokens. 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.