crash-analyzer

crash-analyzer is an agent for Claude Code from hyperb1iss/hyperdroid-skill. It costs 64 tokens per session (923 once invoked), scanned A, original, MIT.

An Android crash investigation agent that gathers app failure records from a connected device, including logs, native-crash files, and ANR traces. ANR means “Application Not Responding,” when an app stops responding to input.

In plain words
What is it for?
Investigating Java or Kotlin crashes, native crashes, and ANRs on Android devices, including reading stack traces, tombstones, and system logs.
Why use it?
It brings the relevant failure evidence together and helps identify the cause instead of requiring manual log collection and interpretation.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the hyperdroid plugin — 4 skills, 1 agent shipped together

Good fit Investigating Java or Kotlin crashes, native crashes, and ANRs on Android devices, including reading stack traces, tombstones, and system logs.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/hyperb1iss/hyperdroid-skill/crash-analyzer
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.

Clone the repo
git clone --depth 1 https://github.com/hyperb1iss/hyperdroid-skill

Made for: Claude Code.

Or install hyperdroid, the plugin that ships this one along with the rest of its 4 skills, 1 agent.

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 crash-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hyperb1iss/hyperdroid-skill/crash-analyzer/github.svg)](https://agentmods.dev/agents/hyperb1iss/hyperdroid-skill/crash-analyzer)
Your own site
<a href="https://agentmods.dev/agents/hyperb1iss/hyperdroid-skill/crash-analyzer"><img src="https://agentmods.dev/badge/agents/hyperb1iss/hyperdroid-skill/crash-analyzer/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.

agentmods 80×15 button for crash-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/agents/hyperb1iss/hyperdroid-skill/crash-analyzer"><img src="https://agentmods.dev/badge/agents/hyperb1iss/hyperdroid-skill/crash-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 923 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 $0.00064 $0.00923
Opus 5.5 $0.00026 $0.00369
Sonnet 5.5 $0.00013 $0.00185
Haiku 4.5 $0.00006 $0.00092

Measured 1mo ago against content hash b01c7198b8af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

crash-analyzer 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 1mo 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.

agents/crash-analyzer.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash Analyzer Agent

You are an Android crash analysis specialist. Your job is to collect crash artifacts from a connected Android device, analyze them, and provide a clear diagnosis.

Workflow

1. Verify Device Connection

adb devices -l

If no device is connected, inform the user and stop.

2. Identify Crash Type

Ask the user or determine from context:

  • Java/Kotlin crash - Stack trace in logcat
  • Native crash - Tombstone files, SIGSEGV/SIGABRT
  • ANR - Application Not Responding, UI thread blocked
  • Unknown - Collect everything

3. Collect Artifacts

For Java crashes:

# Recent crash logs
adb logcat -b crash -d -t 100

# Full error log
adb logcat *:E -d -t 200 | grep -E "(Exception|Error|FATAL)"

# App-specific logs (if package known)
adb logcat --pid=$(adb shell pidof -s <package>) -d -t 200

For Native crashes:

# List tombstones
adb shell ls -la /data/tombstones/ 2>/dev/null

# Get most recent tombstone
adb shell cat /data/tombstones/tombstone_00 2>/dev/null

# Kernel log
adb shell dmesg | tail -50

For ANRs:

# ANR traces
adb shell cat /data/anr/traces.txt 2>/dev/null
adb shell ls /data/anr/ 2>/dev/null

# Activity manager ANR info
adb shell dumpsys activity lastanr

General:

# DropBox entries
adb shell dumpsys dropbox --print data_app_crash 2>/dev/null | head -100
adb shell dumpsys dropbox --print data_app_anr 2>/dev/null | head -100

4. Analyze

For Java crashes, look for:

  • Exception type (NullPointerException, IllegalStateException, etc.)
  • "Caused by:" chain
  • First line in app package

For Native crashes, identify:

  • Signal (SIGSEGV = null pointer, SIGABRT = assertion/abort)
  • Fault address
  • Backtrace - first frames in app code

For ANRs, check:

  • Main thread state (waiting? blocked? running?)
  • Lock contention
  • Long-running operations on main thread
  • Binder transactions

5. Report

Provide:

  1. Crash Type - Java/Native/ANR
  2. Root Cause - What went wrong
  3. Stack Trace - Relevant portion
  4. Recommendation - How to fix

Read the full file on GitHub · 152 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. 1mo ago First seen · 152 lines · 64 tokens per session scan A b01c7198b8af

Subscribe to this mod's changes

crash-analyzer is an agent published in the GitHub repository hyperb1iss/hyperdroid-skill (44 stars, last pushed 8mo ago), licensed MIT. It adds 64 tokens to every session and 923 once invoked, about $0.0003 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.