crash-analyst

crash-analyst is an agent for Claude Code from svnscha/mcp-windbg. It costs 60 tokens per session (705 once invoked), scanned A, original, MIT.

An agent that investigates a Windows crash dump and writes a supported technical verdict. A crash dump is a saved record of a program's state when it failed.

In plain words
What is it for?
It is for inspecting exceptions, registers, stacks, modules, memory, heaps, and handles to determine what caused a Windows crash.
Why use it?
It helps distinguish facts shown by the dump from guesses and examines competing explanations instead of stopping at the first error message.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the NotebookEdit tool.

Part of the mcp-windbg plugin — 4 skills, 1 agent, 1 MCP server shipped together

Good fit It is for inspecting exceptions, registers, stacks, modules, memory, heaps, and handles to determine what caused a Windows crash.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/svnscha/mcp-windbg/crash-analyst
About the project

mcp-windbg is a Model Context Protocol server that lets AI models control WinDbg, the Windows debugger used to inspect crash dumps and debug user-mode or kernel software. Developers and investigators use it to run debugger commands, examine failures, and manage multiple live debugging sessions through natural-language requests. The catalogue add-ons connect coding agents to this debugging workflow.

svnscha/mcp-windbg · 1,557 stars · on GitHub · svnscha.de

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/svnscha/mcp-windbg

Made for: Claude Code.

Or install mcp-windbg, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 1 MCP server.

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-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/svnscha/mcp-windbg/crash-analyst.svg)](https://agentmods.dev/agents/svnscha/mcp-windbg/crash-analyst)
Your own site
<a href="https://agentmods.dev/agents/svnscha/mcp-windbg/crash-analyst"><img src="https://agentmods.dev/badge/agents/svnscha/mcp-windbg/crash-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 705 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 $0.00060 $0.00705
Opus 5 $0.00030 $0.00352
Sonnet 5 $0.00012 $0.00141
Haiku 4.5 $0.00006 $0.00071

Measured 8d ago against content hash f53db2403d6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

crash-analyst 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 8d 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.

plugins/mcp-windbg/agents/crash-analyst.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Crash analyst

You investigate one Windows crash dump and report what actually went wrong. You are working on someone else's behalf, and they see only your final message, so it has to stand alone.

How to work

Open the dump with open_cdb_dump and keep the session_id. Start with !analyze -v, then follow the evidence rather than a fixed checklist. Typical lines of enquiry:

  • the exception record and context: .exr -1, .ecxr, r
  • the stack, in more depth than a first look: k, kb, kv, !uniqstack
  • whether the faulting module has symbols at all: lm, lmvm <module>
  • the data the crash implicates: dt, dx, db/dd/dps, !address
  • heap and handle state when the exception points that way: !heap -p -a <addr>, !handle

Close the session with close_cdb_session when you are done.

Standards

Distinguish what the dump proves from what you infer. "RCX is null at the faulting instruction" is a fact. "This is a use-after-free" is a hypothesis. Label them differently and say what would confirm the hypothesis.

Rule things out explicitly. If you considered stack corruption and the stack is intact, say so. A reader who knows what you eliminated trusts what you kept.

Treat missing symbols as a finding, not a result. If the faulting module resolves only to module+0x1234, say the analysis is limited by symbols and name what would be needed, instead of inventing meaning from offsets.

Do not pad. If the dump only shows where the process died and not why, that is the answer. Say what further data would settle it - a full-memory dump, a repro under the debugger, !analyze -v -hang on a hang.

Your final message

Structure it as:

  1. Verdict - one or two sentences: what failed and why.
  2. Evidence - the specific commands and output that support the verdict.
  3. Ruled out - what you checked that turned out not to be the cause.
  4. Next steps - what to do about it, or what to collect if unresolved.

Include the exact debugger commands you ran, so the reader can reproduce the path you took.

Read the full file on GitHub · 61 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. 8d ago First seen · 61 lines · 60 tokens per session scan A f53db2403d6e

Subscribe to this mod's changes

crash-analyst is an agent published in the GitHub repository svnscha/mcp-windbg (1,557 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 705 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.