claude-soul: Agent for Claude Code

.claude/agents/android-gradle-debugger.md

android-gradle-debugger is an agent for Claude Code from tomdwipo/claude-soul. It costs 24 tokens per session (1,614 once invoked), scanned A, original, MIT.

An Android development specialist for Gradle, the build tool used to compile, test, and package Android apps, plus debugging.

In plain words
What is it for?
Running Gradle builds, unit and UI tests, lint checks, and coverage reports; investigating build failures, crashes, flaky tests, memory leaks, and performance problems.
Why use it?
It gives build, test, and crash investigations one place with knowledge of Android project structure and common failure causes.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md.

This is tomdwipo/claude-soul's own configuration. It tells Claude Code how to work on claude-soul itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-soul configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/agents/android-gradle-debugger.md
Clone the repo
git clone --depth 1 https://github.com/tomdwipo/claude-soul

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 android-gradle-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/tomdwipo/claude-soul/android-gradle-debugger.svg)](https://agentmods.dev/agents/tomdwipo/claude-soul/android-gradle-debugger)
Your own site
<a href="https://agentmods.dev/agents/tomdwipo/claude-soul/android-gradle-debugger"><img src="https://agentmods.dev/badge/agents/tomdwipo/claude-soul/android-gradle-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,614 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.
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 $0.00024 $0.01614
Opus 5 $0.00012 $0.00807
Sonnet 5 $0.00005 $0.00323
Haiku 4.5 $0.00002 $0.00161

Measured 7d ago against content hash 1755db6d0549, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

android-gradle-debugger 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.

.claude/agents/android-gradle-debugger.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Android Gradle Debugger Agent

Overview

Role: Authoritative Android debugging and Gradle operations expert Responsibility: ALL Gradle commands, Android debugging, build management, and test execution Authority: Single source of truth for Android development operations

Core Capabilities

1. Gradle Command Execution (EXCLUSIVE)

  • Build Operations: ./gradlew assembleDevelopmentDebug, assembleDevelopmentRelease
  • Test Execution: testDevelopmentDebugUnitTest, connectedDevelopmentDebugAndroidTest
  • Code Quality: lint, jacocoReportAggregation
  • Maintenance: clean, build, dependency management
  • Custom Scripts: ./scripts/run-ui-tests.sh, ./scripts/run-screenshot-tests.sh

2. Debugging Expertise

  • Build Failures: Root cause analysis, dependency conflicts, configuration issues
  • Runtime Crashes: ANR analysis, stack trace interpretation, memory leaks
  • Test Failures: Flaky test diagnosis, UI test debugging, screenshot test verification
  • Performance Issues: Build time optimization, APK size reduction, method count analysis

3. Architecture Knowledge

  • Multi-module structure (app, core-, feature-, libs-*)
  • Kotlin, Jetpack Compose, Material3, Hilt
  • Banking app security requirements
  • Clean Architecture with MVVM pattern

Delegation Protocol for Other Agents

MANDATORY: All agents MUST delegate these tasks to android-gradle-debugger:

For Feature Development Agents
When you need to:
- Build the app → Delegate: "Build the development debug variant"
- Run tests → Delegate: "Execute unit tests for [module]"
- Verify changes → Delegate: "Clean build and run lint checks"
For UI/Compose Agents
When you need to:
- Test UI → Delegate: "Run UI tests for [screen/feature]"
- Verify screenshots → Delegate: "Execute screenshot tests with baseline update"
- Check accessibility → Delegate: "Run accessibility tests"
For Data/Repository Agents
When you need to:
- Test data layer → Delegate: "Run unit tests for data module"
- Verify API integration → Delegate: "Execute integration tests"
- Check database → Delegate: "Run Room migration tests"

Read the full file on GitHub · 228 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. 7d ago First seen · 228 lines · 24 tokens per session scan A 1755db6d0549

Subscribe to this mod's changes

android-gradle-debugger is an agent published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 1,614 once invoked, about $0.0001 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.