crashdx: Skill for Claude Code

.claude/skills/crash-triage/SKILL.md

crash-triage is a skill for Claude Code from r00tify/crashdx. It costs 71 tokens per session (1,588 once invoked), scanned A, original, MIT.

A tool for investigating Apple crash reports in .ips format, using crashdx and optional dSYMs, which are files that map compiled code back to source names and lines.

In plain words
What is it for?
Use it for app crashes from TestFlight, users, or .ips files: analyze the report, inspect supporting evidence, and connect the likely cause to a code fix.
Why use it?
It turns a difficult-to-read crash report into a symbolicated diagnosis with evidence and ranked possible causes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is r00tify/crashdx's own configuration. It tells Claude Code how to work on crashdx 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 crashdx configures →

Reuse

Borrowing it

Nothing to install: this file belongs to r00tify/crashdx. 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/r00tify/crashdx/main/.claude/skills/crash-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/r00tify/crashdx

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 crash-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/r00tify/crashdx/crash-triage/github.svg)](https://agentmods.dev/skills/r00tify/crashdx/crash-triage)
Your own site
<a href="https://agentmods.dev/skills/r00tify/crashdx/crash-triage"><img src="https://agentmods.dev/badge/skills/r00tify/crashdx/crash-triage/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-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/r00tify/crashdx/crash-triage"><img src="https://agentmods.dev/badge/skills/r00tify/crashdx/crash-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,588 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 $0.00071 $0.01588
Opus 5 $0.00036 $0.00794
Sonnet 5 $0.00014 $0.00318
Haiku 4.5 $0.00007 $0.00159

Measured 10d ago against content hash 5d9bc4d45cc0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

crash-triage 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 10d 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/skills/crash-triage/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apple crash triage with crashdx

The crashdx CLI turns a raw .ips crash report + dSYMs into a symbolicated, diagnosed report. Trust its JSON over your own reading of the raw file; it encodes ground truth about .ips quirks that is easy to get wrong (decimal offsets, LEB symbol degradation, ASI absence patterns).

Invoke it as crashdx if it is on your PATH; otherwise use swift run crashdx … from the repo root, or .build/debug/crashdx after swift build. The commands below use the bare name for brevity.

Procedure

  1. Analyze first, read raw second: crashdx analyze <report.ips> --json --tier summary Summary tier is token-lean (faulting thread capped at 15 frames, plus the verdict and ranked hypotheses). Escalate to --tier standard (adds binary images, other threads containing app frames, and factsConsidered) or full (every thread, uncapped) only when the verdict is inconclusive or you need cross-thread evidence (deadlocks, lock holders). The diagnosis itself is identical at every tier: it is always computed from the full report, so escalating never changes the verdict, only the evidence you can see.

  2. dSYMs. If app frames show only offsets (no symbol), the dSYM wasn't found. Spotlight + Xcode archives are searched automatically; --no-spotlight and --no-archives turn those off, which is how you keep the user's unrelated projects out of the output. For foreign reports (user emails, CI artifacts), pass the build's dSYM with --dsym <path> (repeatable; accepts a .dSYM bundle, an .xcarchive, or a directory to search recursively).

    If the symbolication key is absent entirely, crashdx ran no symbolication pass: either every referenced image already carried symbols (the common case for a report analyzed on the machine that produced it), or nothing was found for the images that needed it. Look at the frames to tell which: if app frames have symbol, nothing was needed. Otherwise check symbolication.images[].outcome:

    • no_dsym: nothing was found. Go get the dSYM.
    • uuid_mismatch: a dSYM for that image WAS found, but it's from a different build, so it was refused (a stale dSYM yields confidently wrong symbols). reason names the offending bundle by absolute path. That path usually sits under the user's ~/Library/Developer/Xcode/Archives/ and can name their other projects; summarise it, don't paste it anywhere shared. Re-run with --no-spotlight --no-archives --dsym <path> to restrict the search to paths the user named. Don't hunt for a missing file; find the archive matching the report's binary UUID. Never force it through.
    • failed: a dSYM matched but symbolication itself failed; reason says why.

Read the full file on GitHub · 104 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. 10d ago First seen · 104 lines · 71 tokens per session scan A 5d9bc4d45cc0

Subscribe to this mod's changes

crash-triage is a skill published in the GitHub repository r00tify/crashdx (7 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,588 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

Swift Performance Optimization Skill

Use when investigating measured Swift or Apple-platform regressions in CPU, memory, launch, scrolling, animation hitches, image processing, energy, networking, or concurrency, or when designing performance tests and Instruments experiments. Do not use for speculative micro-optimization, ordinary refactoring, or a…

termio-sh/termio · 68 tokens

native-app-profiling

Profile native macOS/iOS apps using Time Profiler via CLI (xctrace). Use when asked to identify performance hotspots, profile CPU usage, or diagnose slow code paths without opening Instruments.

termio-sh/termio · 45 tokens

performance-audit

Audit and improve SwiftUI runtime performance. Use for requests to diagnose slow rendering, janky scrolling, high CPU/memory usage, excessive view updates, or layout thrash in SwiftUI apps.

termio-sh/termio · 43 tokens

Debroid CLI Debugger

Orchestrate headless Android debugging via JDWP. ACTIVATE this skill whenever asked to debug an Android application, set line or exception breakpoints, inspect runtime variables or Jetpack Compose state, step through execution, evaluate live expressions, watch fields, or diagnose runtime crashes.

PatilShreyas/debroid · 61 tokens

symbolication-setup

Configure crash symbolication for readable stack traces. Use when setting up dSYMs (iOS), ProGuard/R8 mappings (Android), or source maps (React Native).

nexus-labs-automation/mobile-observability · 40 tokens

network-tracing

Instrument API requests with spans and distributed tracing. Use when tracking request latency, correlating client-backend traces, or debugging API issues.

nexus-labs-automation/mobile-observability · 31 tokens