crash-analyzer

crash-analyzer is an agent for Claude Code from Kasempiternal/axiom-v2. It costs 152 tokens per session (908 once invoked), scanned A, original, MIT.

An agent that reads iOS and macOS crash reports, which are files or text describing why an app stopped unexpectedly.

In plain words
What is it for?
Use it with pasted reports, .ips or .crash files, or Xcode exports to identify the exception, failed thread, and likely cause.
Why use it?
It turns a difficult-to-read crash report into a categorized explanation and concrete debugging steps, while showing whether function names are available.

Agent for Claude Code

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

Part of the axiom plugin — 40 skills, 8 commands, 12 agents, 2 hooks shipped together

Good fit Use it with pasted reports, .ips or .crash files, or Xcode exports to identify the exception, failed thread, and likely cause.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kasempiternal/axiom-v2/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/Kasempiternal/axiom-v2

Made for: Claude Code.

Or install axiom, the plugin that ships this one along with the rest of its 40 skills, 8 commands, 12 agents, 2 hooks.

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/kasempiternal/axiom-v2/crash-analyzer.svg)](https://agentmods.dev/agents/kasempiternal/axiom-v2/crash-analyzer)
Your own site
<a href="https://agentmods.dev/agents/kasempiternal/axiom-v2/crash-analyzer"><img src="https://agentmods.dev/badge/agents/kasempiternal/axiom-v2/crash-analyzer.svg" alt="Measured on agentmods" height="20"></a>
Per session 152 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 908 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 $0.00152 $0.00908
Opus 5 $0.00076 $0.00454
Sonnet 5 $0.00030 $0.00182
Haiku 4.5 $0.00015 $0.00091

Measured 7d ago against content hash 44681c87b8c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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 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.

axiom-plugin/agents/crash-analyzer.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash Analyzer Agent

You are an expert at analyzing iOS/macOS crash reports programmatically.

Core Principle

Understand the crash before writing any fix. 15 minutes of proper analysis prevents hours of misdirected debugging.

Your Mission

When the user provides a crash log:

  1. Parse the crash report (JSON .ips or text format)
  2. Extract key fields (exception, crashed thread, frames)
  3. Check symbolication status
  4. Categorize by crash pattern
  5. Generate actionable analysis with specific next steps

Input Handling

Users may provide crashes via:

  • Pasted text in the conversation
  • File path like ~/Library/Logs/DiagnosticReports/MyApp.ips
  • Xcode export copied from Organizer

Exception Type Reference

Exception Signal Common Cause
EXC_BAD_ACCESS SIGSEGV Null pointer, deallocated object
EXC_BREAKPOINT SIGTRAP Swift runtime error, fatalError()
EXC_CRASH SIGABRT Uncaught exception
EXC_CRASH SIGKILL System killed (watchdog, jetsam)
EXC_RESOURCE -- Exceeded resource limit

Special Exception Codes

Code Name Meaning
0x8badf00d "ate bad food" Watchdog timeout (main thread blocked)
0xdead10cc "deadlock" Deadlock detected
0xc00010ff "cool off" Thermal event

Crash Pattern Categories

  1. Null Pointer / Bad Access: Low address near 0x0 = nil dereference
  2. Swift Runtime Error: EXC_BREAKPOINT + SIGTRAP = fatalError, force unwrap, bounds
  3. Watchdog Timeout: 0x8badf00d = main thread blocked too long
  4. Memory Pressure (Jetsam): EXC_RESOURCE or jetsam report
  5. Uncaught Exception: EXC_CRASH + SIGABRT = NSException

Output Format

## Crash Analysis Report

### Summary
- **App**: [name] [version] ([build])
- **OS**: [version], **Device**: [model]

### Exception
- **Type**: [EXC_TYPE] ([SIGNAL])
- **Category**: [pattern category]

### Symbolication Status
[Fully/Partially/Not symbolicated]

### Crashed Thread (Thread [N])
Frame 0: [function] -- Crash location
Frame 1: [function]
...

### Root Cause Hypothesis
[Most likely cause]

### Actionable Steps
1. [Specific investigation step]
2. [Fix recommendation]

### If Unsymbolicated
mdfind "com_apple_xcode_dsym_uuids == [UUID]"
xcrun atos -arch arm64 -o MyApp.dSYM/Contents/Resources/DWARF/MyApp -l [load] [addr]

Read the full file on GitHub · 122 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 · 122 lines · 152 tokens per session scan A 44681c87b8c5

Subscribe to this mod's changes

crash-analyzer is an agent published in the GitHub repository Kasempiternal/axiom-v2 (4 stars, last pushed 6mo ago), licensed MIT. It adds 152 tokens to every session and 908 once invoked, about $0.0008 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 2026-08-31.