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.
npx agentmods add agents/hyperb1iss/hyperdroid-skill/crash-analyzergit clone --depth 1 https://github.com/hyperb1iss/hyperdroid-skillWhat 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 | $0.00064 | $0.00923 |
| Opus 5 | $0.00032 | $0.00462 |
| Sonnet 5 | $0.00013 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
crash-analyzer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crash Analyzer Agent
You are an Android crash analysis specialist. Your job is to collect crash artifacts from a connected Android device, analyze them, and provide a clear diagnosis.
Workflow
1. Verify Device Connection
adb devices -l
If no device is connected, inform the user and stop.
2. Identify Crash Type
Ask the user or determine from context:
- Java/Kotlin crash - Stack trace in logcat
- Native crash - Tombstone files, SIGSEGV/SIGABRT
- ANR - Application Not Responding, UI thread blocked
- Unknown - Collect everything
3. Collect Artifacts
For Java crashes:
# Recent crash logs
adb logcat -b crash -d -t 100
# Full error log
adb logcat *:E -d -t 200 | grep -E "(Exception|Error|FATAL)"
# App-specific logs (if package known)
adb logcat --pid=$(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:
- Crash Type - Java/Native/ANR
- Root Cause - What went wrong
- Stack Trace - Relevant portion
- Recommendation - How to fix
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.
- 2d ago First seen · 152 lines · 64 tokens per session scan A b01c7198b8af
crash-analyzer is an agent published in the GitHub repository hyperb1iss/hyperdroid-skill (35 stars, last pushed 7mo ago), licensed MIT. It adds 64 tokens to every session and 923 once invoked, about $0.0003 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.
Other agents, from other repositories
token-caching-researcher
Gathers information on token caching, subprocess isolation, and cost-control in Claude Code. Triggers on: research token caching, check subprocess overhead, find caching rules.
fixer
Apply code-level fixes for user-approved FAIL items. Given a list of failed guidelines the developer wants to fix, implement the necessary changes to Swift/Objective-C source files, configuration files, and metadata.
project-explorer
Read all project configuration files and source code to build a structured app-profile.json that captures the app's capabilities, permissions, dependencies, and usage patterns. This profile becomes the input for the Guideline Auditor.
plan-writer
Generate comprehensive ASO plan with keywords, metadata, visuals, and localization strategy.
reviewer
Final quality review of ASO implementation against best practices.
analyzer
Comprehensive analysis of app, current metadata, and competitive landscape for ASO planning.