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)<a href="https://agentmods.dev/skills/melandlabs/openloomi/openloomi"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi/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"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi.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 | $0.00155 | $0.01553 |
| Opus 5 | $0.00077 | $0.00776 |
| Sonnet 5 | $0.00031 | $0.00311 |
| Haiku 4.5 | $0.00015 | $0.00155 |
Grade B, and why
openloomi scanned grade B 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 9d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
| `install-hooks` | `/openloomi:hooks install` | Merge hooks into `~/.claude/settings.json` | How it starts
The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenLoomi Claude Plugin Skill
This skill is the single entry point for the OpenLoomi ↔ Claude Code
integration. It is intentionally thin: it delegates to
loomi-bridge.mjs for every side effect and never duplicates OpenLoomi
business logic, connector implementations, or memory storage.
When to call loomi-bridge
Call loomi-bridge.mjs whenever ANY of the following is true:
- User says
openloomi,loomi,pet,/openloomi:*, or asks about "the local AI assistant". - User wants to install, configure, verify, or update OpenLoomi.
- User asks Claude Code to query their memory, look up a previous conversation, or "search my notes".
- User wants to set the Loomi Pet to a specific state.
- User wants today's LLM cost / usage.
- User asks about hooking Claude Code up to "the pet" or "loop".
When the user just wants something Claude can do natively (write a file, answer a question, etc.) and OpenLoomi is not mentioned, do not invoke the bridge.
Bridge subcommands (quick reference)
| Subcommand | Slash command | Typical use |
|---|---|---|
setup |
/openloomi:setup |
First-run install + status |
setup-status [--json] |
/openloomi:status |
Stable JSON status |
install [--yes] |
(internal) | User-approved install |
login |
(internal) | Open OpenLoomi login surface, report status |
pet <state> |
/openloomi:pet |
Set Pet state (9 universal states; theme-agnostic) |
state <name> |
(internal/hook) | Fire-and-forget Pet state from hook |
archive |
(internal/hook) | Archive last transcript on Stop |
usage |
/openloomi:usage |
Today's LLM usage summary |
install-hooks |
/openloomi:hooks install |
Merge hooks into ~/.claude/settings.json |
uninstall-hooks |
/openloomi:hooks uninstall |
Strip only the plugin's hook block |
hooks-status |
/openloomi:hooks status |
Report hook merge state |
loop (doorway) |
/openloomi:loop |
Loop dashboard snapshot — delegates to the openloomi-loop sub-skill |
memory <query> (doorway) |
/openloomi:memory |
Search memory + KB + insights — delegates to the openloomi-memory sub-skill |
version |
(internal) | Print plugin version |
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.
- 9d ago First seen · 125 lines · 155 tokens per session scan B d531c7e891e1
openloomi is a skill published in the GitHub repository melandlabs/openloomi (1,023 stars, last pushed 9d ago), licensed Apache-2.0. It adds 155 tokens to every session and 1,553 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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…
algorithmic-art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright…
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external agents through well-designed tools. Use when building MCP servers to integrate external APIs or agents, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
self-improvement
A process for recording useful lessons from unexpected failures, user corrections, missing abilities, and reusable project patterns.