harmonyos-device-automation

harmonyos-device-automation is a skill for Claude Code from web-infra-dev/midscene-skills. It costs 164 tokens per session (4,373 once invoked), scanned A, original, MIT.

A screenshot-based automation skill for controlling HarmonyOS NEXT devices through natural-language actions. HarmonyOS NEXT is an operating system, and HDC is the tool used to communicate with its devices.

In plain words
What is it for?
Use it to tap, type, swipe, drag, press system buttons, and perform other actions on a HarmonyOS device based on what appears on screen.
Why use it?
It can interact with visible parts of an app even when there is no usable page structure or accessibility information to inspect.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is npx -y @midscene/harmony@1 report-tool --action to-markdown --htmlPath ./midscene_run/report/.../index.html --outputDir ./output-markdown.

Good fit Use it to tap, type, swipe, drag, press system buttons, and perform other actions on a HarmonyOS device based on what appears on screen.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/web-infra-dev/midscene-skills
agentmods
npx agentmods add skills/web-infra-dev/midscene-skills/harmony-automation

Made for: Claude Code.

Wrote 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.

agentmods badge for harmonyos-device-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/web-infra-dev/midscene-skills/harmony-automation/github.svg)](https://agentmods.dev/skills/web-infra-dev/midscene-skills/harmony-automation)
Your own site
<a href="https://agentmods.dev/skills/web-infra-dev/midscene-skills/harmony-automation"><img src="https://agentmods.dev/badge/skills/web-infra-dev/midscene-skills/harmony-automation/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.

agentmods 80×15 button for harmonyos-device-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/web-infra-dev/midscene-skills/harmony-automation"><img src="https://agentmods.dev/badge/skills/web-infra-dev/midscene-skills/harmony-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 164 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,373 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00164 $0.04373
Opus 5 $0.00082 $0.02187
Sonnet 5 $0.00033 $0.00875
Haiku 4.5 $0.00016 $0.00437

Measured 9d ago against content hash 80d91a1cad8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harmonyos-device-automation 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 9d 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.

skills/harmony-automation/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HarmonyOS Device Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:

  1. Never run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop.
  2. Run only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together.
  3. Allow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer.

Automate HarmonyOS NEXT devices using npx -y @midscene/harmony@1. Each CLI command maps directly to an MCP tool — you (the AI agent) act as the brain, deciding which actions to take based on screenshots.

What act Can Do

Inside a single act call on HarmonyOS, Midscene can tap, double-tap, long-press, type, clear text, scroll, drag items, press keys, and use system navigation such as Back, Home, or recent apps while working from the current visible screen. Two-finger zoom is not available because the underlying HarmonyOS automation layer does not expose multi-touch input.

Prerequisites

Midscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):

MIDSCENE_MODEL_API_KEY="your-api-key"
MIDSCENE_MODEL_NAME="model-name"
MIDSCENE_MODEL_BASE_URL="https://..."
MIDSCENE_MODEL_FAMILY="family-identifier"

Example: Gemini (Gemini-3-Flash)

MIDSCENE_MODEL_API_KEY="your-google-api-key"
MIDSCENE_MODEL_NAME="gemini-3-flash"
MIDSCENE_MODEL_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai/"
MIDSCENE_MODEL_FAMILY="gemini"

Read the full file on GitHub · 322 lines

Changes

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.

  1. 9d ago First seen · 322 lines · 164 tokens per session scan A 80d91a1cad8b

Subscribe to this mod's changes

harmonyos-device-automation is a skill published in the GitHub repository web-infra-dev/midscene-skills (307 stars, last pushed yesterday), licensed MIT. It adds 164 tokens to every session and 4,373 once invoked, about $0.0008 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.

Related

Other skills, from other repositories