MiMoCode is a terminal-based AI coding assistant that reads and writes code, runs commands, manages Git, and remembers project context across sessions. Developers use it to work with software projects through a command-line interface and connect it to language-model providers; the catalogue includes skills and instructions for it.
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 XiaomiMiMo/MiMo-Code --skill url-to-codegit clone --depth 1 https://github.com/XiaomiMiMo/MiMo-CodeWrote 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/xiaomimimo/mimo-code/url-to-code)<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/url-to-code"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/url-to-code/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/xiaomimimo/mimo-code/url-to-code"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/url-to-code.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00024 | $0.00531 |
| Opus 5.5 | $0.00010 | $0.00212 |
| Sonnet 5.5 | $0.00005 | $0.00106 |
| Haiku 4.5 | $0.00002 | $0.00053 |
Grade A, and why
url-to-code 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
URL to Code
Use this workflow only when the user asks to clone or faithfully recreate a live site they own or have permission to reproduce. For redesign, improvement, or a loosely inspired result, route through ../index/SKILL.md to context and ideation instead.
Read ../index/SKILL.md, ../../references/critical-overrides.md, and relevant saved context before building.
Workflow
- Remind the user that they must have permission and follow the target site's terms.
- Open the source with the browser selected by the index. Stop if it resolves to a wrong page, login wall, error, unrelated redirect, or other surface that cannot ground the requested clone.
- Capture the full desktop page and a representative mobile viewport. Inspect small scroll increments so sticky, lazy-loaded, and animated content is not missed.
- Inspect the DOM and visible behavior for text, links, controls, component states, images, icons, fonts, colors, spacing, dimensions, breakpoints, and interaction behavior.
- Test important interactions one at a time and return to the starting state between tests. Preserve evidence for changed states.
- Save permitted source assets locally. Do not hotlink them in the final result. When an asset cannot be obtained, use an available generation tool or an appropriate open replacement and disclose the substitution.
- Inspect the target repository and use its existing framework and conventions. React is not required. If no app exists, create the smallest suitable frontend supported by the harness; plain HTML/CSS/JavaScript is acceptable.
- Build only from captured evidence. Implement the visible desktop/mobile layouts and primary interactions without inventing unrelated design choices or backend behavior.
- Run and inspect the local implementation with a real browser. Compare the same viewport and states against the source.
- Run
../design-qa/SKILL.md, savedesign-qa.md, fix blocking and high-impact mismatches, and hand off only afterfinal result: passedor a clearly documented verification blocker.
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.
- 1mo ago First seen · 34 lines · 24 tokens per session scan A 560083987d3f
url-to-code is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (13,683 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 531 once invoked, about $0.0001 per session on Opus 5.5. 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
opencli-autofix
Automatically fix broken OpenCLI adapters when commands fail. Load this skill when an opencli command fails — it guides you through collecting a trace artifact, patching the adapter, retrying, and filing an upstream GitHub issue after a verified fix. Works with any AI agent.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
browser
Drives a real browser through the omowright library from the js eval kernel: sites the user is already signed into, forms and clicks, JS-rendered pages, screenshots, web QA, extension popups, a human handoff for login, CAPTCHA or OTP, and a browser you own for scraping, bot-scored targets, network capture and QA…
harbor-daytona
Use Harbor's Daytona sandbox platform for computer use — creating sandboxes, taking screenshots, sending mouse/keyboard input, and building agent loops. Use when the user wants to interact with a GUI, automate a desktop, do computer use, control a browser visually, or run Claude computer use against a Daytona sandbox.
agent-browser
Browser automation via Chrome/Chromium CDP — open, snapshot, click, screenshot. For testing web apps, mobile layouts, and automated interactions without Playwright/Puppeteer.
webcmd-browser
Use when a live browser task requires Playwright interaction, authenticated handoff, visible UI verification, or ad-hoc page inspection.