Claude-Tools-for-Delphi: Skill for Claude Code

.claude/skills/light-bug-Android/SKILL.md

light-bug-Android is a skill for Claude Code from GabrielOnDelphi/Claude-Tools-for-Delphi. It costs 146 tokens per session (2,244 once invoked), scanned A, original, MPL-2.0.

A Delphi Android crash-triage agent that investigates an app from a computer through ADB, the Android debugging command-line tool. It collects logs, classifies the failure, and helps match native crash addresses to compiled code.

In plain words
What is it for?
Use it to investigate Delphi FMX Android crashes, collect logcat and application logs, identify the failure type, and symbolicate stripped native-library addresses using the linker map.
Why use it?
It replaces guesswork with captured device evidence and separates Pascal, Java, native, deployment, and IDE-related failures.

Skill for Claude Code

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

This is GabrielOnDelphi/Claude-Tools-for-Delphi's own configuration. It tells Claude Code how to work on Claude-Tools-for-Delphi 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-Tools-for-Delphi configures →

Reuse

Borrowing it

Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. 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/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-bug-Android/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-Delphi

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 light-bug-Android

README.md
[![agentmods](https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-android.svg)](https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-android)
Your own site
<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-android"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-bug-android.svg" alt="Measured on agentmods" height="20"></a>
Per session 146 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,244 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00146 $0.02244
Opus 5 $0.00073 $0.01122
Sonnet 5 $0.00029 $0.00449
Haiku 4.5 $0.00015 $0.00224

Measured 2d ago against content hash 1bcf0847cc28, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

light-bug-Android 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (Tools/MapLookup.ps1), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/skills/light-bug-Android/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/light-bug-Android — FMX Android crash triage (PC-side, over adb)

When invoked, do this in order. Be terse. Full background knowledge (classification table, .map recipe, paths) is in Reference - Android crash triage.md in this skill's folder — read it once at the start.

Constants:

ADB = c:\Delphi\Delphi 13\CatalogRepository\AndroidSDK-37.0.59082.6021\platform-tools\adb.exe
CaptureDir = c:\AI\Claude Code\Temp

If that CatalogRepository\AndroidSDK-* folder does not exist, glob for the actual installed version — the embedded SDK number drifts between Delphi updates.

Step 0 — Resolve device + package

  1. & $ADB devices — need at least one device in device state. unauthorized almost always means an OLD standalone adb daemon (circa 2014) is running and answering instead of the Delphi-bundled one: taskkill /f /im adb.exe, then retry with the bundled path.
  2. Package name: from the user's words, else grep the project's .dproj for package= (in VerInfo_Keys), else AndroidManifest.template.xml. Confirm it is installed: & $ADB shell pm path <pkg>.
  3. If no project is obvious from the working directory, ask which app.

Step 1 — Capture the evidence

Pick by situation:

  • Crash already happened, no tail was running: one-shot dump, unfiltered: & $ADB logcat -d > "$CaptureDir\logcat-<Tag>-dump.txt" 2>&1
  • Crash is reproducible: clear first (& $ADB logcat -b all -c), start an unfiltered capture in the background, have the human reproduce on the phone (or drive it yourself via the mcp__autopilot-android__* tools IF the build has the Autopilot bridge compiled in — AUTOPILOT define), then stop and read the capture.
  • A human at the machine can instead double-click a Logcat-Android.cmd wrapper kept beside the project (verbs: tail/dump/clear; writes to $CaptureDir\logcat-<Tag>-latest.txt).

Capture UNFILTERED. Filter afterwards while reading: the interesting tags are AndroidRuntime (Java FATAL EXCEPTION), DEBUG (native tombstone), and info (Pascal-side FMX.Types.Log.d, prefixed FMX: <AppTitle>:).

Read the full file on GitHub · 103 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 Changed 1bcf0847cc28
  2. 4d ago Changed · +10 lines 58922b294088
  3. 8d ago First seen · 93 lines · 146 tokens per session scan A 849e55a31373

Subscribe to this mod's changes

light-bug-Android is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (17 stars, last pushed today), licensed MPL-2.0. It adds 146 tokens to every session and 2,244 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

ios-fix

Autonomous iOS bug fixer. (gstack).

garrytan/gstack · 15 tokens

google-mobile-ads-validate

Validates a project's Google Mobile Ads (GMA) SDK integration for iOS, Android, or Unity projects. Use when conducting a full pre-launch audit of an app that integrates GMA SDK or when validating any individual GMA SDK integration checks, such as when validating ad unit IDs and ad formats, SKAdNetwork IDs, mediation…

google/skills · 84 tokens

competition-ios-runtime

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for IPA runtime analysis, Frida hooks, Objective-C or Swift method tracing, Keychain inspection, SSL pinning bypass, URL scheme handling, and iOS request-signing recovery. Use when the user asks to hook an IPA, trace Objective-C or Swift…

zhaoxuya520/reverse-skill · 123 tokens

swiftui-performance-audit

SwiftUI performance: render, scroll, CPU/memory, updates, layout, Instruments.

steipete/agent-scripts · 24 tokens

android-tombstone-symbolication

Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…

dotnet/skills · 176 tokens

node-connect

Diagnose OpenClaw node connection and pairing failures for Android, iOS, and macOS companion apps. Use when QR/setup code/manual connect fails, local Wi-Fi works but VPS/tailnet does not, or errors mention pairing required, unauthorized, bootstrap token invalid or expired, gateway.bind, gateway.remote.url, Tailscale…

the-open-agent/openagent · 81 tokens