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 html-to-video-pipelinegit 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/html-to-video-pipeline)<a href="https://agentmods.dev/skills/xiaomimimo/mimo-code/html-to-video-pipeline"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/html-to-video-pipeline/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/html-to-video-pipeline"><img src="https://agentmods.dev/badge/skills/xiaomimimo/mimo-code/html-to-video-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
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 →
- high Tool Misuse · line 73 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
- medium MCP Rug Pull · line 50 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 51 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 54 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Privilege Escalation · line 73 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 76 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
- medium Privilege Escalation · line 92 Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
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 | $0.00000 | $0.04331 |
| Opus 5.5 | $0.00000 | $0.01732 |
| Sonnet 5.5 | $0.00000 | $0.00866 |
| Haiku 4.5 | $0.00000 | $0.00433 |
Grade B, and why
html-to-video-pipeline scanned grade B with 1 finding 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo apt-get update && sudo apt-get install -y ffmpeg How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
HTML → Video: the pipeline that actually works
Turning a live HTML page into an MP4 sounds like a one-liner ("Playwright records, ffmpeg encodes") and the first draft always looks fine — until you play back the export and notice text flashing in a fallback font, three dead seconds at the start, or a "10-second" clip that clocks in at 35s. This skill captures the specific ordering, waits, and encoder flags that make the output trustworthy.
Think of the pipeline as five phases with a single invariant between them:
launch → hold @ frame 0 → align capture start with animation start → record → trim & encode
The invariant: no pixel of the animation should render before capture is ready, AND capture must not start before every asset that affects layout has loaded. Every gotcha below is a violation of that invariant.
Quick checklist (each item is expanded below):
viewportmust exactly equalrecordVideo.size— mismatch silently rescales the output soft/blurry.- Freeze CSS animations via
addInitScriptbeforegoto(). gotowithdomcontentloaded, neverload.- Pre-inline
data-composition-srcsub-scenes —file://blocks client-sidefetch. - Font wait = stylesheet
<link>load →face.load()per face →fonts.ready→ 2 rAFs. - Probe duration with infinite-iteration /
repeat: -1guards. - Unfreeze = t=0; trim
leadInMs − 120mswith-ssbefore-i. - Concat: same engine → demuxer
-c copy; mixed engines → concat filter + re-encode. - Verify with ffprobe duration + full decode + sampled frames. Always.
There are two capture modes, and picking the wrong one wastes a day:
- Mode A — real-time
recordVideo(the phases below). Simple, wall-clock = clip length. But the screencast is best-effort variable frame rate (~25fps) and competes with the animation for CPU. Good enough for previews and ≤30fps deliverables on an idle machine. - Mode B — deterministic frame stepping (pause everything, seek to
i / fps, screenshot, encode the PNG sequence). Exact fps, every frame rendered, no lead-in trim, immune to machine load. Required when the output must be genuinely smooth ≥30fps or renders run on loaded CI. See "Deterministic frame stepping" below.
What ships with it
7 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.
- 1mo ago First seen · 237 lines · 0 tokens per session scan B 94c8e9144f8f
html-to-video-pipeline is a skill published in the GitHub repository XiaomiMiMo/MiMo-Code (13,683 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,331 tokens. A static security scan graded it B with 1 finding (asks for root). 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.