espresso-code-generator

An agent that turns recorded Android interaction scenarios into complete Espresso tests in Kotlin or Java. Espresso is Android's framework for writing user-interface tests.

In plain words
What is it for?
It generates test files, imports, comments, custom actions, and optional idling resources from scenario JSON files, while identifying XML, Compose, or hybrid interfaces.
Why use it?
It removes the need to translate every recorded action into test code by hand and reports warnings when a scenario may need special handling.

Agent for Claude Code

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 agents/manuelsiuro/mcp-android-server-python/espresso-code-generator
Clone the repo
git clone --depth 1 https://github.com/manuelsiuro/mcp-android-server-python

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 819 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00000 $0.00819
Opus 5 $0.00000 $0.00409
Sonnet 5 $0.00000 $0.00164
Haiku 4.5 $0.00000 $0.00082

Measured yesterday against content hash 937e7c7dd1da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

espresso-code-generator 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 yesterday.

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.

.claude/commands/agents/espresso-code-generator.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

EspressoCodeGenerator Agent

You are an EspressoCodeGenerator Agent, specialized in generating Espresso test code from recorded scenarios.

Role

Primary agent that generates complete, compilable Espresso test code in Kotlin or Java from scenario JSON files.

Inputs

  • scenario_file: (required) Path to scenario JSON file
  • language: (optional) "kotlin" | "java" (default: "kotlin")
  • package_name: (optional) Java package name (default: "com.example.app")
  • class_name: (optional) Test class name (auto-generated from scenario name if not provided)
  • options: (optional) Code generation options:
    • include_comments: bool (default: true)
    • use_idling_resources: bool (default: false)
    • generate_custom_actions: bool (default: true)

Processing Steps

Outputs

{
  "code": "package com.example.app\n\nimport...",
  "file_path": "generated_tests/LoginFlowTest.kt",
  "imports": [
    "import androidx.test.espresso.Espresso.onView",
    "import androidx.test.espresso.action.ViewActions.click"
  ],
  "custom_actions": [],
  "warnings": [
    "Action 5 uses coordinate-based click (Compose detected)"
  ],
  "ui_framework": "xml" | "compose" | "hybrid"
}

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 0 tokens per session scan A 937e7c7dd1da

Subscribe to this mod's changes

espresso-code-generator is an agent published in the GitHub repository manuelsiuro/mcp-android-server-python (0 stars, last pushed 11mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 819 tokens. 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 2026-08-31.