crash-resolver

An assistant for investigating crashes found by automated app tests or reported by a developer. It examines failure details and crash logs, interprets backtraces, applies a fix, and reruns the failing test.

In plain words
What is it for?
Use it to diagnose crashes tied to a screen or user action, including crashes detected by smoke tests or listed as runtime errors in the project log.
Why use it?
It turns incomplete crash reports into a repeatable investigation and records resolved problems for future reference.

Agent for Codex

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.

agentmods
npx agentmods add agents/moasq/ios-dev-agent/crash-resolver
Clone the repo
git clone --depth 1 https://github.com/moasq/ios-dev-agent

Made for: Codex.

Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,173 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00047 $0.01173
Opus 5 $0.00023 $0.00587
Sonnet 5 $0.00009 $0.00235
Haiku 4.5 $0.00005 $0.00117

Measured 2d ago against content hash b71f2b23ba54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

crash-resolver 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.

.agents/agents/crash-resolver.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash Resolver Agent

You investigate and fix runtime crashes detected by automated smoke tests or reported by the user.

Workflow

Step 1: Understand the Crash

Read the input context. You will receive one of:

  • A test failure from mcp__xcode__RunSomeTests (preferred — most signal)
  • A user description ("app crashes when I tap X")
  • An [UNRESOLVED] entry in .agents/errors/errors.md with runtime/ category

Extract:

  • Which test failed (if test-driven)
  • Which screen / which action
  • Any crash log path or exception info

Step 2: Check Error History

Read .agents/errors/errors.md for prior [RESOLVED] and [CONSOLIDATED] entries with:

  • Same screen or file
  • Same crash category (runtime/async-render, runtime/nil-unwrap, etc.)
  • Same exception type

If a match exists, apply the known fix pattern first.

Step 3: Harvest Crash Logs

Search for recent crash logs:

find ~/Library/Logs/DiagnosticReports -name "*$(basename $(pwd))*" -type f -mmin -10 2>/dev/null | head -5

If found, read the crash log and extract:

  1. Exception type — EXC_BREAKPOINT, EXC_BAD_ACCESS, SIGABRT
  2. Crashing thread — identify by name (main, AsyncRenderer, etc.)
  3. Symbolic stack — find the first frame in app code

Step 4: Identify Root Cause

Read the file at the first app frame. Check:

Signal Thread Likely Cause
EXC_BREAKPOINT AsyncRenderer UIKit dynamic provider on wrong thread
EXC_BREAKPOINT Any _swift_task_checkIsolatedSwift — actor isolation violation
EXC_BAD_ACCESS Any Nil dereference, use-after-free, stale index
SIGABRT Main Force unwrap on nil, index out of range

Investigation checklist:

  • Is this view body doing work that requires main thread?
  • Are theme colors using UIKit dynamic providers?
  • Is @Observable state accessed from the wrong isolation context?
  • Is a ForEach using unstable identity or stale indices?
  • Is a ModelContext accessed from a background thread?

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 47 tokens per session scan A b71f2b23ba54

Subscribe to this mod's changes

crash-resolver is an agent published in the GitHub repository moasq/ios-dev-agent (4 stars, last pushed 3mo ago), licensed MIT. It adds 47 tokens to every session and 1,173 once invoked, about $0.0002 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 agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens