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 continual-learngit 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/continual-learn)<a href="https://agentmods.dev/skills/melandlabs/openloomi/continual-learn"><img src="https://agentmods.dev/badge/skills/melandlabs/openloomi/continual-learn.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00364 |
| Opus 5 | $0.00028 | $0.00182 |
| Sonnet 5 | $0.00011 | $0.00073 |
| Haiku 4.5 | $0.00006 | $0.00036 |
Grade A, and why
continual-learn 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 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.
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.
What it actually says
You must maintain a real workspace file, MENTAL_MODEL.md, as your durable scratchpad for this task.
Non-negotiable file workflow
- Use
./MENTAL_MODEL.mdin the current workspace; create it if it does not exist. - At the start of each turn, consult the current file when possible.
- Before every final answer or structured task response, perform an actual filesystem write that creates or updates
MENTAL_MODEL.md. - This file write is required even when the task says the final response must contain only JSON or another strict schema. The write happens before the final response; the final response must still obey the requested schema exactly.
- If a dedicated file-write/edit operation is available, use it. Otherwise, use any available shell/filesystem operation to write the file.
What to record
Keep notes terse, high-signal, and actionable:
- Task goal, current plan, and open assumptions.
- Feedback received and what it changes.
- Durable lessons, repo/task quirks, commands tried, and observed failures.
- Hypotheses being tested and evidence for/against them.
- Current state and the next concrete action.
- If nothing meaningful changed, still update a short "latest turn" line so the file write occurs.
Hygiene
- Keep the file compact; rewrite or prune stale notes as needed.
- Do not store secrets, raw datasets, large traces, or unrelated transcript dumps.
Always write MENTAL_MODEL.md before responding.
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 · 33 lines · 55 tokens per session scan A 293ca0f5377a
continual-learn is a skill published in the GitHub repository melandlabs/openloomi (1,023 stars, last pushed 8d ago), licensed Apache-2.0. It adds 55 tokens to every session and 364 once invoked, about $0.0003 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…
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".
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.
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).
self-improvement
A process for recording useful lessons from unexpected failures, user corrections, missing abilities, and reusable project patterns.