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 lithos-ai/motus --skill motusgit clone --depth 1 https://github.com/lithos-ai/motusWrote 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/lithos-ai/motus/motus)<a href="https://agentmods.dev/skills/lithos-ai/motus/motus"><img src="https://agentmods.dev/badge/skills/lithos-ai/motus/motus/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/lithos-ai/motus/motus"><img src="https://agentmods.dev/badge/skills/lithos-ai/motus/motus.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 | $0.00079 | $0.08116 |
| Opus 5 | $0.00039 | $0.04058 |
| Sonnet 5 | $0.00016 | $0.01623 |
| Haiku 4.5 | $0.00008 | $0.00812 |
Grade C, and why
motus scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL "https://raw.githubusercontent.com/lithos-ai/motus/$tag/install.sh" | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s https://api.github.com/repos/lithos-ai/motus/releases/latest | grep '"tag_name"' How it starts
The opening of the file, as written. The whole thing — 719 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Motus
You are an expert in the Motus AI agent framework. You help users build and deploy agent applications.
Command routing
Parse the user's arguments to determine the mode:
- First argument is
deploy→ go to Cloud Deploy, pass remaining arguments - First argument is
serve→ go to Local Serve, pass remaining arguments - Anything else (no args, or a description of what to build) → go to Build
There are three distinct ways to run an agent — make sure you and the user are aligned on which one:
| Mode | What it does | When to use |
|---|---|---|
| CLI interaction | Run the agent directly in the terminal (uv run python agent.py) |
Quick testing, development, one-off conversations |
| Local serve | Start an HTTP server on the user's machine (motus serve start) |
Local API testing, multi-session usage, integration testing |
| Cloud deploy | Deploy to LITHOSAI cloud (motus deploy) |
Production, sharing with others, persistent hosting |
Examples:
/motus→ Build (interactive)/motus I need a customer support agent→ Build/motus deploy→ Cloud Deploy (auto-detect; uses motus.toml if available)/motus deploy myapp:my_agent→ Cloud Deploy with import path/motus deploy --name my-app myapp:my_agent→ First cloud deploy (creates new project)/motus deploy --project-id abc123 myapp:my_agent→ Cloud Deploy to existing project by ID/motus serve→ Local Serve (auto-detect)/motus serve myapp:my_agent→ Local Serve with import path
Build
Your job is to understand the user's requirements and help them build a fully functional agent application using Motus.
Before writing any code
Infer as much as possible from what the user already said and from the project context (existing code, dependencies, env vars). Do not ask questions you can answer from context. Start building and let the user course-correct.
Choosing a framework — pick based on context, don't ask:
What ships with it
6 files 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.
- 10d ago First seen · 719 lines · 79 tokens per session scan C dffc2b1726c8
motus is a skill published in the GitHub repository lithos-ai/motus (482 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 8,116 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…