analyze-crash

analyze-crash is a command for Claude Code from SetsunaYukiOvO/x64dbg-mcp. It costs 8 tokens per session (773 once invoked), scanned A, original, MIT.

A structured investigation of why a program crashed, connected to x64dbg or x32dbg, which are debuggers for Windows programs. It examines the failing instruction, registers, memory, and call stack—the chain of functions that led to the crash.

In plain words
What is it for?
Use it to investigate read or write violations, null or suspicious pointer values, invalid memory regions, and corrupted stack frames in 32-bit or 64-bit Windows software.
Why use it?
It replaces guesswork with evidence about the faulting address, invalid pointers, and damaged memory or stack data. This helps distinguish likely root causes from symptoms.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

Part of the skills plugin — 1 skill, 11 commands shipped together

Good fit Use it to investigate read or write violations, null or suspicious pointer values, invalid memory regions, and corrupted stack frames in 32-bit or 64-bit Windows software.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/setsunayukiovo/x64dbg-mcp/analyze-crash
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/SetsunaYukiOvO/x64dbg-mcp

Made for: Claude Code.

Or install skills, the plugin that ships this one along with the rest of its 1 skill, 11 commands.

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 analyze-crash

README.md
[![agentmods](https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/analyze-crash/github.svg)](https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/analyze-crash)
Your own site
<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/analyze-crash"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/analyze-crash/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 analyze-crash

Your own site · 80×15
<a href="https://agentmods.dev/commands/setsunayukiovo/x64dbg-mcp/analyze-crash"><img src="https://agentmods.dev/badge/commands/setsunayukiovo/x64dbg-mcp/analyze-crash.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 773 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 $0.00008 $0.00773
Opus 5 $0.00004 $0.00387
Sonnet 5 $0.00002 $0.00155
Haiku 4.5 $0.00001 $0.00077

Measured 12d ago against content hash 2f04550049e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

analyze-crash 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 12d 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.

skills/commands/analyze-crash.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a crash analysis expert connected to x64dbg/x32dbg via MCP. Perform a systematic crash analysis.

Phase 1: Crash Context Collection

  1. Call debug_get_state to confirm the debugger is paused at an exception.
  2. Call register_list to capture ALL register values. Check for:
    • RIP (x64) / EIP (x86): the faulting instruction address
    • Registers with suspicious values: 0x0, 0xDEADBEEF, 0xCCCCCCCC, 0xFEEEFEEE, very small values (NULL+offset)
  3. Call disassembly_at with the crash address (or the current instruction pointer, cip, if "$1" is empty) and count: 30.
  4. Call stack_get_trace for the full call stack.
  5. Call stack_get_pointers to verify stack frame integrity.

Phase 2: Memory State Analysis

  1. For each register used as a pointer in the faulting instruction:
    • Call memory_get_info to check if the memory region is valid, readable, writable, executable.
    • If valid, call memory_read with size 64-128 bytes to inspect content.
  2. If crash is a write violation, examine the destination address.
  3. If crash is a read violation, examine the source address.
  4. Call memory_read on the stack area around the current stack pointer (csp, ~256 bytes) to inspect stack contents.

Phase 3: Execution History

  1. Disassemble the calling function via disassembly_function or disassembly_at with count: 50 on the caller address from the stack.
  2. Call symbol_from_address on the crash address to identify the owning module/function.
  3. Call module_get for the module containing the crash.
  4. Call function_get at the crash address to find the function boundaries.
  5. Call xref_get on the crash function to find who called it.

Phase 4: Root Cause Classification

Classify the crash as one of:

  • NULL pointer dereference: Register used as pointer is 0 or near-zero
  • Use-After-Free: Pointer to freed heap memory (often 0xFEEEFEEE on Windows debug heap)
  • Buffer overflow: Stack corruption, overwritten return address, or heap metadata corruption
  • Stack overflow: RSP (x64) / ESP (x86) pointing outside the stack region
  • DEP violation: Attempting to execute non-executable memory
  • Integer overflow: Bad calculation result used as size/offset
  • Uninitialized memory: Register contains 0xCCCCCCCC (debug fill)
  • Double free: Crash inside RtlFreeHeap or similar heap functions

Read the full file on GitHub · 73 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. 12d ago First seen · 73 lines · 8 tokens per session scan A 2f04550049e1

Subscribe to this mod's changes

analyze-crash is a command published in the GitHub repository SetsunaYukiOvO/x64dbg-mcp (463 stars, last pushed 22d ago), licensed MIT. It adds 8 tokens to every session and 773 once invoked, about $0.0000 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.