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/commands/melandlabs/openloomi/tour)<a href="https://agentmods.dev/commands/melandlabs/openloomi/tour"><img src="https://agentmods.dev/badge/commands/melandlabs/openloomi/tour.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00571 |
| Opus 5 | $0.00015 | $0.00285 |
| Sonnet 5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade B, and why
tour 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(node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs *), Bash(node ${CLAUDE_PLUGIN_ROOT}/skills/openloomi-connectors/scripts/openloomi-connectors.cjs *), Bash(node ${CLAUDE_PLUGIN_ROOT}/skills/openloom Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
allowed-tools: Bash(node ${CLAUDE_PLUGIN_ROOT}/scripts/loomi-bridge.mjs *), Bash(node ${CLAUDE_PLUGIN_ROOT}/skills/openloomi-connectors/scripts/openloomi-connectors.cjs *), Bash(node ${CLAUDE_PLUGIN_ROOT}/skills/openloom What it actually says
/openloomi:tour
Thin doorway into the openloomi-tour
sub-skill. The skill runs the full first-run pipeline live with
checkpoints between phases:
- Pre-flight (
setup-status,run-host-probe, selected execution-provider readiness) - Pet reaction (4 sprite states cycled)
- Connector onboarding (native bot vs Composio OAuth — user picks)
- Run one Loop tick + inspect & approve a decision card
- Seed Memory (
add-memory× 3 +search-all) - Optional extensions: custom Loop channel / classifier rule / decision type
The skill is the source of truth — read it first for the exact shell snippets per phase. This doorway just confirms the entry point.
Steps
- Confirm
setup: ready(or run/openloomi:setupfirst if not). - Load the
openloomi-tourskill and execute its phases in order. Stop between phases for the user to react (next/skip/back). - On exit (
done,exit, or all five phases complete), print the quick-reference card from the/openloomi:setuppost-ready walkthrough.
When to suggest
- "I just installed OpenLoomi, what now?" →
/openloomi:tour - "Show me everything OpenLoomi can do" →
/openloomi:tour - "Walk me through the pipeline" →
/openloomi:tour - "带我看一下" / "体验一下" / "一条龙" →
/openloomi:tour
For everything inside the tour (specific commands, decision card
shapes, channel registration payloads), say the trigger phrase from
the openloomi-tour frontmatter
and Claude will pick the right subcommand.
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 · 44 lines · 29 tokens per session scan B bf54462ca75c
tour is a command published in the GitHub repository melandlabs/openloomi (1,022 stars, last pushed 7d ago), licensed Apache-2.0. It adds 29 tokens to every session and 571 once invoked, about $0.0001 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 commands, from other repositories
explain
A guided command for explaining how a file or code section works. It covers its purpose, main logic, data flow, dependencies, design choices, and possible improvements.
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
agentlas-local
Staff a task only from Agentlas agents registered on this machine.
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.