agentmods.dev

mobile-harness AGENTS.md

Repository instructions for Mobile Harness, a project for operating Android and iOS devices through its standard control interface.

In plain words
What is it for?
Use them before mobile work to update the project, install its dependencies when needed, and route platform actions through Mobilerun.
Why use it?
They define the required setup and loading order so agents use the supported device-control path and keep runtime packages current.

Instructions file for CodexOpenCode

338 +5 8d ago A scan 879 tokens original MIT
View the source file droidrun/mobile-harness
Install

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.

agentmods
npx agentmods add instructions/droidrun/mobile-harness/agents-md
Clone the repo
git clone --depth 1 https://github.com/droidrun/mobile-harness

Made for: Codex, OpenCode.

Per session 879 This file is loaded in full into every session.
When invoked 879 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
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 $0.00879 $0.00879
Opus 5 $0.00439 $0.00439
Sonnet 5 $0.00176 $0.00176
Haiku 4.5 $0.00088 $0.00088

Measured 2d ago against content hash b3f720e4db8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mobile-harness AGENTS.md scanned grade A 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Treat raw ADB, Android Portal HTTP curl, and iOS Portal curl as setup, diagnostics, or recovery paths only.
AGENTS.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Mobile Harness

This repository tells an AI agent how to operate Android and iOS devices through existing control surfaces.

Normal device control always goes through from mobilerun_core import Mobilerun. Do not import local drivers directly for ordinary agent work.

Load Order

  1. Update once per session, before platform work (<harness-root> is the directory containing this AGENTS.md):
    • git -C <harness-root> pull --ff-only
    • <harness-root>/.venv/bin/python -m pip install -U "mobilerun-core[local]" mobilerun-core-local mobilerun-sdk The explicit mobilerun-core-local and mobilerun-sdk entries keep those runtime packages upgraded even when they are already satisfied transitive dependencies. Agents should still import only mobilerun_core. If <harness-root>/.venv does not exist yet (a fresh clone or a fresh skills-CLI copy), skip this step and read install.md first. Skip the pip step if the libraries are pinned. Run the git pull only if <harness-root>/.git exists; without it (for example a copy installed with the skills CLI), git -C operates on an enclosing repository — run npx skills update from the project where the skill was installed instead. If offline, continue with the current version. On any other failure, read UPDATE.md.
  2. Decide the target platform before acting.
  3. For Android work, read platforms/android/GUIDE.md.
  4. For iOS work, read platforms/ios/GUIDE.md.
  5. Do not load all files.
  6. When the foreground app id is known, read only that app card if it exists:
    • Android: apps/android/<package>/CARD.md
    • iOS: apps/ios/<bundle-id>/CARD.md
  7. Read platform recovery only after a control, setup, state, or connectivity failure.
  8. Read the credentials guide under core/credentials when a screen asks for login, API keys, OTP, 2FA, payment, passcode, or other secrets.
  9. Write to <harness-root>/credentials/<app-id>.md only when the user explicitly asks for local credential files.
  10. Read core/memory/GUIDE.md before reading or writing files under <harness-root>/memory/.

Read the full file on GitHub · 50 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. 2d ago First seen · 50 lines · 879 tokens per session scan A b3f720e4db8c

Subscribe to this mod's changes

mobile-harness AGENTS.md is an instructions file published in the GitHub repository droidrun/mobile-harness (338 stars, last pushed 8d ago), licensed MIT. It adds 879 tokens to every session, about $0.0044 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Mobileai-harnessclaude-codecodexmobile-aimobile-development
Related

Other instructions, from other repositories

MobiAI-Core CLAUDE.md

Instructions for ArisGuimera/MobiAI-Core, covering mobiai — mobile development ai ecosystem, bootstrap and principles.

ArisGuimera/MobiAI-Core · 159 tokens

freetube CLAUDE.md

Instructions for leshkodev/freetube, covering claude.md, 1. what this project is, 2. non-negotiable constraints, 3. tech stack (locked) and 4. project structure.

leshkodev/freetube · 9,979 tokens

ConsultMe CLAUDE.md

Instructions for Tarek-Bohdima/ConsultMe, covering claude.md, project context, common commands, module graph and conventions enforced by tooling.

Tarek-Bohdima/ConsultMe · 3,021 tokens

claude-status CLAUDE.md

Instructions for gmr/claude-status, covering claude.md, project overview, build & test, platform & language and dependencies (spm).

gmr/claude-status · 2,613 tokens

DensityToggle CLAUDE.md

Instructions for channelramble/DensityToggle, covering density toggle - wear os display density control, goal, current status, how it works and how auto mode decides (v5).

channelramble/DensityToggle · 3,642 tokens

phone-mcp CLAUDE.md

Instructions for premex-ab/phone-mcp, covering claude.md, project overview, build commands, architecture and module layout.

premex-ab/phone-mcp · 2,128 tokens