pet

pet is a command for coding agents from melandlabs/openloomi. It costs 24 tokens per session (501 once invoked), scanned A, original, Apache-2.0.

A command that changes the state of the OpenLoomi Pet, a small on-screen companion, such as idle, thinking, working, or happy.

In plain words
What is it for?
Use it to set one of the supported pet states through the provided command. Some states are rejected by the service and should be left to the Loop baseline watcher.
Why use it?
It gives the companion a defined state that can reflect what is happening during an agent session.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the openloomi plugin — 11 skills, 10 commands, 8 hooks shipped together

About the project

OpenLoomi is an open-source desktop AI coworker that connects work tools, gathers context, and highlights decisions or actions needing attention. It is for people managing work across multiple apps, and its catalogue add-ons extend the resident desktop for agent frameworks such as Claude Code, Codex, OpenCode, Hermes, and OpenClaw.

melandlabs/openloomi · 1,021 stars · on GitHub

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/melandlabs/openloomi/pet
Clone the repo
git clone --depth 1 https://github.com/melandlabs/openloomi

Or install openloomi, the plugin that ships this one along with the rest of its 11 skills, 10 commands, 8 hooks.

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 pet

README.md
[![agentmods](https://agentmods.dev/badge/commands/melandlabs/openloomi/pet.svg)](https://agentmods.dev/commands/melandlabs/openloomi/pet)
Your own site
<a href="https://agentmods.dev/commands/melandlabs/openloomi/pet"><img src="https://agentmods.dev/badge/commands/melandlabs/openloomi/pet.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 501 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 $0.00024 $0.00501
Opus 5 $0.00012 $0.00251
Sonnet 5 $0.00005 $0.00100
Haiku 4.5 $0.00002 $0.00050

Measured 5d ago against content hash 2d96e5490777, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

pet 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 5d 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.

plugins/claude/commands/pet.md · 49 lines

What it actually says

/openloomi:pet

The bridge accepts 9 states for client-side validation:

happy, idle, juggling, needsinput, presenting, sleeping, sweeping, thinking, working.

However, POST /api/pet/state only accepts 7 of these:

idle, thinking, working, juggling, happy, presenting, needsinput.

sleeping and sweeping are capybara-theme vocabulary managed by the Loop baseline watcher — the API returns 400 invalid_state for them. The bridge currently forwards them and surfaces the 400 as PET_FAILED rather than rejecting client-side. Avoid requesting those two from Claude; let the Loop baseline watcher set them.

Run:

node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs pet <state>
  • If the state is one of the 7 API-accepted values, the bridge returns {ok: true, state, response: { ok: true, ... }}.
  • If the state is sleeping / sweeping (bridge accepts but API rejects), the bridge returns {ok: false, code: "PET_FAILED", status: 400, error: { raw: "invalid_state" }}.
  • If the state is anything else, the bridge returns {ok: false, code: "INVALID_STATE", validStates: [...]} client-side without hitting the API.
  • If the POST /api/pet/state endpoint is not yet exposed by OpenLoomi, the bridge returns {ok: false, code: "ENDPOINT_MISSING", ...} with a polite notice. Treat that as a non-blocking outcome for the user.

Tips:

  • Manual idle, sleeping, sweeping, presenting are managed by the loop watcher — changing them from Claude will be quickly overridden.
  • Hooks handle automatic state transitions; /openloomi:pet is for explicit user-driven overrides.
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. 5d ago First seen · 49 lines · 24 tokens per session scan A 2d96e5490777

Subscribe to this mod's changes

pet is a command published in the GitHub repository melandlabs/openloomi (1,021 stars, last pushed 5d ago), licensed Apache-2.0. It adds 24 tokens to every session and 501 once invoked, about $0.0001 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.