Maestro is a testing framework for automating user-interface and end-to-end tests for Android, iOS, and web applications. Testers define interactions in human-readable YAML flows and run them on emulators, simulators, browsers, or real devices. The catalogue includes skills, instructions, and an agent for using Maestro.
Borrowing it
Nothing to install: this file belongs to mobile-dev-inc/Maestro. 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/mobile-dev-inc/Maestro/main/AGENTS.mdgit clone --depth 1 https://github.com/mobile-dev-inc/MaestroWrote 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/mobile-dev-inc/maestro/agents-md)<a href="https://agentmods.dev/instructions/mobile-dev-inc/maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/mobile-dev-inc/maestro/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/mobile-dev-inc/maestro/agents-md"><img src="https://agentmods.dev/badge/instructions/mobile-dev-inc/maestro/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 | $0.03793 | $0.03793 |
| Opus 5.5 | $0.01517 | $0.01517 |
| Sonnet 5.5 | $0.00759 | $0.00759 |
| Haiku 4.5 | $0.00379 | $0.00379 |
Grade A, and why
Maestro 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 16d 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Maestro
Shared context for any Claude Code skill or subagent operating in this repo. Skills (.claude/skills/*) reference this file rather than restating module roles; if a description here drifts from reality, fix it here once and every skill follows.
Commits, pull requests, and anything else you publish
This is a public repo. Anything pushed or posted is published permanently: commits, branch names, code and comments, test fixtures and flows, PR and issue text, review comments. Never:
- Publish secrets, tokens, credentials, or sensitive
.envcontents. - Add AI-attribution trailers (
Co-authored-by:for a tool, "Generated with…", session links), orSigned-off-by.
Staff contributors only: if you know which customer, org, or deployment a change is for — from a tracker, Slack, or Maestro Cloud — that's staff context and must not reach the repo. Don't name them, and don't include what identifies them: their app's package or bundle ID, flows or screenshots from their app, Cloud IDs or dashboard URLs, or an internal tracker's contents. Reference trackers by ID only (MA-1234, #3504). Reproduce against the demo app, not their app.
Full rules — PR title and body, sensitive info: docs/pull-requests.md; issues: docs/issues.md. Opening a PR or issue with --body (gh pr create, gh issue create) skips the templates in .github/, so read the matching doc first and use its headings. Open a PR as ready for review when it is; open it as a draft only when there's a reason not to ask for a human yet, such as checking CI passes.
Module map
Top-level Gradle modules. Code lives under each module's src/main/.
| Module | Role |
|---|---|
maestro-android/ |
On-device Android driver. Kotlin sources compile to two checked-in APKs (maestro-app.apk, maestro-server.apk) consumed by maestro-client/. The build's copyMaestroAndroid / copyMaestroServer finalizers update those APKs plus a maestro-android-source.sha256 checksum. |
maestro-ios-driver/ |
Host side of iOS driver wrapper (Kotlin). The actual XCTest runner lives in maestro-ios-xctest-runner/. |
maestro-ios-xctest-runner/ |
Swift XCTest runner that runs on the iOS device/simulator. The compiled artifacts (maestro-driver-ios*.zip) are checked in under maestro-ios-driver/src/main/resources/driver-iPhoneSimulator/Debug-iphonesimulator/. |
maestro-ios/ |
iOS host-side glue (small — most iOS host code lives in maestro-client/). |
maestro-client/ |
Host-side Kotlin SDK that drives devices. Platform drivers live in src/main/java/maestro/drivers/: AndroidDriver.kt, IOSDriver.kt, WebDriver.kt, CdpWebDriver.kt. This is where most "auto-grant", "auto-dismiss", system-dialog handling and platform-specific quirks belong. |
maestro-orchestra/ |
Command execution layer. Orchestra.kt interprets each Maestro command, applies retries, manages the command lifecycle. Sub-packages: error/, filter/, workspace/, yaml/. |
maestro-orchestra-models/ |
Shared command/data models (used by maestro-orchestra/ and consumers). |
maestro-cli/ |
CLI entry point + MCP server. Mixed Kotlin (~100 files) + Swift (~56 files for iOS-related CLI bits). |
maestro-utils/ |
Shared utilities. |
maestro-web/ |
Web (browser) driver pieces. |
maestro-proto/ |
Protobuf definitions shared across modules. |
maestro-test/ |
Cross-module tests that doesn't require devices. |
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.
- 16d ago Changed · +11 lines · +317 tokens per session 76701617882e
- 26d ago Changed · +8 lines · +147 tokens per session 1f47ce4662db
- 28d ago Changed · +1 lines · +158 tokens per session 8bc0c0161575
- 1mo ago First seen · 135 lines · 3,171 tokens per session scan A 6156767260be
Maestro AGENTS.md is an instructions file published in the GitHub repository mobile-dev-inc/Maestro (16,251 stars, last pushed yesterday), licensed Apache-2.0. It adds 3,793 tokens to every session, about $0.0152 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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.