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.
Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melandlabs/openloomi/plugin install openloomiWrote 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.
[](https://agentmods.dev/skills/melandlabs/openloomi/openloomi-pet)<a href="https://agentmods.dev/skills/melandlabs/openloomi/openloomi-pet"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi-pet/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/melandlabs/openloomi/openloomi-pet"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi-pet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00110 | $0.01874 |
| Opus 5 | $0.00055 | $0.00937 |
| Sonnet 5 | $0.00022 | $0.00375 |
| Haiku 4.5 | $0.00011 | $0.00187 |
Grade A, and why
openloomi-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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenLoomi Pet Sub-skill
The Loomi Pet has 9 universal state names. The plugin ships the fox
(loomi-*) sprite set for branding; the OpenLoomi runtime's
state-resolution watcher renders the matching sprite for whichever
theme you have active (fox or capybara, or any folder under
~/.openloomi/pet-custom/). State set:
| State | When to use |
|---|---|
happy |
A task just completed successfully |
idle |
Loomi is waiting for the next loop tick (watcher-only — do not set from Claude) |
juggling |
Multiple sub-agents are running |
needsinput |
Permission prompt / elicitation dialog visible |
presenting |
Fresh decision requires the user's review (watcher-only — do not set from Claude) |
sleeping |
Local hour outside 6–22 with no pending work (watcher-only — do not set from Claude) |
sweeping |
User dismissed a card just now (watcher-only) |
thinking |
Between steps, awaiting LLM response |
working |
A tool call is in progress (PreToolUse hook fires this) |
Available commands
node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs pet <state>— synchronous, returns JSON; use only when the user explicitly asks.- Hooks call
state <name>automatically (fire-and-forget, 2s timeout).
Sprite set is hardcoded in the bridge — invalid state names are rejected
before any HTTP call. The endpoint POST /api/pet/state may not yet exist
in the target OpenLoomi runtime; the bridge falls back to "would have set
state to X — pending OpenLoomi endpoint" without raising an error.
Help the user customize their pet's appearance
The bridge only drives the state — sprite overrides and theme folders
are file-based and live outside the plugin. When the user asks to "change
the pet's look" or "add a custom character", walk them through the file
system. Do not try to write pet-config.json from the bridge; the
bridge has no such command and the runtime's file watcher does the work.
Decision tree
- "I just want the other built-in" → right-click Loomi →
Theme → Fox/Theme → Capybara. Persisted in~/.openloomi/pet-config.jsonunderactiveTheme. Long-press (~600 ms) is the fallback ifcontextmenuis swallowed by the host. - "I want my own character" → drop a folder at
~/.openloomi/pet-custom/<name>/with PNGs named after the states. The watcher auto-discovers it within ~250 ms and the theme appears in the menu. - "I want to change just one sprite" → edit
~/.openloomi/pet-config.json'soverridesmap. Wins over both built-ins and custom-theme sprites for the matching(theme, state)pair. - "I want to make my theme the default" → set
activeThemeto the custom theme's folder name.
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.
- 11d ago First seen · 116 lines · 110 tokens per session scan A 68e3fe33fb48
openloomi-pet is a skill published in the GitHub repository melandlabs/openloomi (1,025 stars, last pushed 10d ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,874 once invoked, about $0.0006 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.
Other skills, from other repositories
harness-creator
Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md/CLAUDE.md instruction files, feature/state tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is…
building-mobile-game
Build mobile games and game-like interactive experiences in React Native and Expo. Use when Codex is creating or refactoring arcade, puzzle, casual, action, physics-based, or animation-heavy gameplay, including Expo game setup with the with-reanimated template, sprite-sheet generation and extraction, frame-based…
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
stream-unity
Build, integrate, and answer how-to questions for Stream Chat and Stream Video in Unity Engine games and apps. Use for Unity / C# / MonoBehaviour project work - the Chat .unitypackage and the Video UPM package, StreamChatClient / StreamVideoClient wiring, ConnectUserAsync and tokens, channels and messages, calls and…
stream-unreal
Build, integrate, and answer how-to questions for Stream Chat in Unreal Engine games and apps. Use for Unreal Engine / UE5 / C++ / Blueprint / UMG project work - plugin install per engine version, StreamChatClientComponent wiring on the HUD, ConnectUser and tokens, channels and messages, the shipped WBP chat widgets…
winning-avg-corewars
Guidance for developing CoreWars warriors that achieve target win rates against specific opponents. This skill should be used when tasks involve writing, optimizing, or debugging Redcode assembly warr.