Borrowing it
Nothing to install: this file belongs to droidrun/mobile-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/droidrun/mobile-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/droidrun/mobile-harnessWrote 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/instructions/droidrun/mobile-harness/agents-md)<a href="https://agentmods.dev/instructions/droidrun/mobile-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/droidrun/mobile-harness/agents-md/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/instructions/droidrun/mobile-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/droidrun/mobile-harness/agents-md.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 | $0.00941 | $0.00941 |
| Opus 5.5 | $0.00376 | $0.00376 |
| Sonnet 5.5 | $0.00188 | $0.00188 |
| Haiku 4.5 | $0.00094 | $0.00094 |
Grade A, and why
mobile-harness AGENTS.md 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 7d 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 — 56 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.
Control devices through mobilerun_core (from mobilerun_core import Mobilerun);
mobilerun-core-local is its internal driver dependency.
Load Order
- Check the installed Python environment once per session, before platform work.
<harness-root>contains thisAGENTS.md.<state-root>holds.venv/andlocal/; it is<harness-root>unlessSKILL.mdset it to another directory. Use the interpreter named in the user's agent instructions, otherwise<state-root>/.venv/bin/python. With that interpreter as<python>, run<python> -c "from mobilerun_core import Mobilerun; from importlib.metadata import version; print('mobilerun-core', version('mobilerun-core'))". If the environment or dependency is missing, first check the interpreter path, then readinstall.mdfor setup. Otherwise use the installed versions. Do not fetch, pull, runnpx skills update, or install/upgrade packages as a routine startup step. ReadUPDATE.mdonly when the user requests an update or a confirmed version incompatibility blocks the task. Preserve pinned versions unless the user authorizes changing them. - Decide the target platform and backend before acting. For a local backend,
also check
<python> -c "from importlib.metadata import version; print('mobilerun-core-local', version('mobilerun-core-local'))".PackageNotFoundErroris a setup issue; cloud-only work does not require it. - For Android work, read
platforms/android/GUIDE.md. - For iOS work, read
platforms/ios/GUIDE.md. - Do not load all files.
- 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.mdThen read the same path under<state-root>/local/apps/if it exists. That file is the user's own and wins wherever it disagrees with the shipped card; it may also be the only card that exists.
- Android:
- Read platform recovery only after a control, setup, state, or connectivity failure.
- Read the credentials guide under
core/credentialswhen a screen asks for login, API keys, OTP, 2FA, payment, passcode, or other secrets. - Write to
<state-root>/local/credentials/<app-id>.mdonly when the user explicitly asks for local credential files. - Read
core/memory/GUIDE.mdbefore reading or writing files under<state-root>/local/memory/.
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.
- 7d ago Changed · -1 lines · -4 tokens per session 2668f79e5f08
- 14d ago Changed · +6 lines · +15 tokens per session ba8a3c6ed044
- 1mo ago Changed · +1 lines · +51 tokens per session 071c8012f4c2
- 1mo ago First seen · 50 lines · 879 tokens per session scan A b3f720e4db8c
mobile-harness AGENTS.md is an instructions file published in the GitHub repository droidrun/mobile-harness (421 stars, last pushed 7d ago), licensed MIT. It adds 941 tokens to every session, about $0.0038 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.