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
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.
npx skills add melandlabs/openloomi --skill openloomi-loopgit clone --depth 1 https://github.com/melandlabs/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-loop)<a href="https://agentmods.dev/skills/melandlabs/openloomi/openloomi-loop"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/openloomi-loop.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 4 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 101 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00171 | $0.02921 |
| Opus 5 | $0.00086 | $0.01460 |
| Sonnet 5 | $0.00034 | $0.00584 |
| Haiku 4.5 | $0.00017 | $0.00292 |
Grade B, and why
openloomi-loop scanned grade B with 2 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 8d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
allowed-tools: Bash(curl *), Bash(jq *), Bash(cat ~/.openloomi/token *), Bash(base64 -d *), Bash(ls ~/.openloomi/loop/*), Read(~/.openloomi/loop/custom-types.json), Read(~/.openloomi/loop/custom-channels.json), Read(~/.o Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(curl *), Bash(jq *), Bash(cat ~/.openloomi/token *), Bash(base64 -d *), Bash(ls ~/.openloomi/loop/*), Read(~/.openloomi/loop/custom-types.json), Read(~/.openloomi/loop/custom-channels.json), Read(~/.o How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Note: If you haven't downloaded or installed openloomi yet, please refer to Getting Started for installation instructions.
OpenLoomi Loop — The Proactive Execution Brain
Loop pulls signals from connected integrations, classifies them into typed decisions, and lets the user approve execution from the pet or the web UI. This skill is a thin Claude-side wrapper around Loop's HTTP API.
Where things live
| Concern | Location |
|---|---|
| Business logic | Loop's TypeScript core (closed DecisionType + classifier + scheduler) |
| HTTP API | /api/loop/* — state, decisions, decision/[id], card/[id], connectors, brief, wrap, tick, preferences, action/*, types, types/[id], channels, channels/[id], classifier-rules, classifier-rules/[id], classifier-rules/dry-run |
| Persistence | ~/.openloomi/loop/{signals.jsonl,decisions.json,status.json,connectors.json,config.json} |
| Scheduler | Three ScheduledJob rows: loop.tick, loop.brief, loop.wrap (registered by the loop scheduler) |
| Pet surface | Tauri Rust thread loomi-pet-decision-watcher polls decisions.json mtime every 2s and emits loop:state / loop:decision to bubble + card webviews. The widget supports two built-in themes (fox, capybara) and a presenting state surfaced when a decision moves to done before the user has reviewed it — click the bubble to flip back to happy. User-editable theme config lives at ~/.openloomi/pet-config.json. |
Base URL
| Environment | Base |
|---|---|
| Local desktop (Tauri) — default | http://localhost:3414 |
Dev server (pnpm dev, pnpm tauri:dev) |
http://localhost:3515 |
If unsure, start with http://localhost:3414. Loop ships inside the
desktop bundle; the dev port is only relevant when you're running
the web app standalone.
Auth
Per-user routes (/tick, /decision/[id] POST, /preferences,
/action/*) require the same auth as the rest of the app. Token is
the base64-encoded JWT stored at ~/.openloomi/token — decode it
before use:
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 195 lines · 171 tokens per session scan B cd3e941aff6c
openloomi-loop is a skill published in the GitHub repository melandlabs/openloomi (1,022 stars, last pushed 7d ago), licensed Apache-2.0. It adds 171 tokens to every session and 2,921 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
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".
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…
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output. Use when: (1) monitoring Claude/Codex sessions running in tmux, (2) sending input to interactive terminal applications, (3) scraping output from long-running processes inside tmux, (4) navigating tmux panes/windows…
cron
Use when the user asks to schedule recurring tasks, one-off reminders, timers, or cron-style jobs through the OpenSquilla cron tool.
agent-initialization
Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.
meta-scheduled-morning-digest
Compose a morning digest combining local weather, news for the user's interest topic, a structured summary, and a memory note.