autonomy_analyse

autonomy_analyse is a command for Claude Code from valory-xyz/open-autonomy. It costs 0 tokens per session (2,728 once invoked), scanned A, original, Apache-2.0.

A group of checks for examining and verifying AI agents, including consistency checks for their state-machine skills. A state machine is a defined set of states and rules for moving between them.

In plain words
What is it for?
Use it to analyse agent documentation and run verification subcommands such as docstring checks.
Why use it?
It helps find problems in an agent's documented behavior before relying on it. For example, it can check whether an agent's state-machine documentation follows the expected format.

Command for Claude Code

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

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is autonomy analyse fsm-specs --package ./packages/valory/skills/hello_world_abci.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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_analyse

README.md
[![agentmods](https://agentmods.dev/badge/commands/valory-xyz/open-autonomy/autonomy_analyse.svg)](https://agentmods.dev/commands/valory-xyz/open-autonomy/autonomy_analyse)
Your own site
<a href="https://agentmods.dev/commands/valory-xyz/open-autonomy/autonomy_analyse"><img src="https://agentmods.dev/badge/commands/valory-xyz/open-autonomy/autonomy_analyse.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 2,728 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 $0.02728
Opus 5 $0.00000 $0.01364
Sonnet 5 $0.00000 $0.00546
Haiku 4.5 $0.00000 $0.00273

Measured 6d ago against content hash 8b943b65f3a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

autonomy_analyse 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_analyse.md · 415 lines

How it starts

The opening of the file, as written. The whole thing — 415 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tools for analysing and verifying AI agents.

This command group consists of a number of functionalities to analyse and verify AI agents, including {{fsm_app}} skill consistency checks. See the appropriate subcommands for more information.

autonomy analyse docstrings

Analyse {{fsm_app}} skill docstring definitions.

This command verifies that the AbciApp class docstring is follows a standard format.

??? example

The docstring corresponding to the [Hello World AI agent](https://stack.olas.network/demos/hello-world/) is


```python
"""HelloWorldAbciApp

Initial round: RegistrationRound

Initial states: {RegistrationRound}

Transition states:
    1. RegistrationRound
        - done: 1.
    2. CollectRandomnessRound
        - done: 2.
        - no majority: 1.
        - round timeout: 1.
    3. SelectKeeperRound
        - done: 3.
        - no majority: 0.
        - round timeout: 0.
    4. PrintMessageRound
        - done: 4.
        - round timeout: 0.
    5. ResetAndPauseRound
        - done: 1.
        - no majority: 0.
        - reset timeout: 0.

Final states: {}

Timeouts:
    round timeout: 30.0
    reset timeout: 30.0
"""
```

Usage

autonomy analyse docstrings [OPTIONS]

Options

--update : Update docstrings if required.

--help : Show the help message and exit.

Examples

To analyse all the {{fsm_app}} skill docstrings within the local registry, run the following command in the directory containing the registry:

autonomy analyse docstrings

To update/fix the {{fsm_app}} skill docstrings, run the following command:

autonomy analyse docstrings --update

autonomy analyse fsm-specs

Verify the {{fsm_app}} against its specification or generate the {{fsm_app}} specification file.

Usage

Usage: autonomy analyse fsm-specs [OPTIONS]

Read the full file on GitHub · 415 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 · 415 lines · 0 tokens per session scan A 8b943b65f3a5

Subscribe to this mod's changes

autonomy_analyse 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 2,728 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.