Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Cdb Windows Debug

ASecurity

Debug native Windows programs and crash dumps via the devtools-mcp cdb backend (batch-mode CDB). Use when a Windows .exe crashes, you have a .dmp file, or you need all-thread stacks / a crash bucket without a GUI debugger. Covers !analyze -v triage, ~*k thread stacks, register/locals inspection, installing cdb, and symbol setup. Headless and scriptable, the Windows analog of the LLDB debug tools.

9 stars
0 votes
0 copies
0 views
Added 9/27/2026
ai-agentsdebuggingbackend

Works with

mcp

Security Analysis

A100/100

Scanned 9/27/2026

$npx -y skills add Ugbot/ai-grind --skill cdb-windows-debug --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cdb Windows Debug?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Cdb Windows Debug
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/ugbot-cdb-windows-debug/badge)](https://www.skillsdirectory.com/skills/ugbot-cdb-windows-debug)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: cdb-windows-debug
description: >
  Debug native Windows programs and crash dumps via the devtools-mcp cdb backend
  (batch-mode CDB). Use when a Windows .exe crashes, you have a .dmp file, or you
  need all-thread stacks / a crash bucket without a GUI debugger. Covers
  !analyze -v triage, ~*k thread stacks, register/locals inspection, installing
  cdb, and symbol setup. Headless and scriptable, the Windows analog of the
  LLDB debug tools.
---

# Windows debugging with CDB (devtools-mcp `cdb:*`)

The `cdb` backend runs CDB, the console Windows debugger, in batch mode:
a scripted `-c "...;q"` command sequence, captured and parsed into a structured
snapshot. No interactive console, so it's safe to run headless. Three tools:

| tool | CDB script | use for |
|---|---|---|
| `analyze` | `!analyze -v` | crash triage: exception code, faulting module, bucket |
| `stacks` | `~*kn` | every thread's backtrace (hangs, deadlocks, "where is it") |
| `inspect` | `kn; r` | current backtrace + registers |

## Install cdb

cdb ships with **Debugging Tools for Windows** (Windows SDK) or
`winget install Microsoft.WinDbg`. The backend finds it via `$DEVTOOLS_CDB`,
PATH, or the SDK `Debuggers\x64` folder. `devtools_check()` shows whether it's
available and how to install it.

## Triage a crash dump

```
devtools_run(suite="cdb", tool="analyze", binary="", extra_args=["--dump","C:/dumps/app.dmp"])
```

The summary surfaces the key `!analyze -v` fields, namely `EXCEPTION_CODE`,
`SYMBOL_NAME`, `MODULE_NAME`, and `FAILURE_BUCKET_ID`, plus the faulting thread's top
frames. Then drill in:

```
devtools_analyze(run_id, function_pattern="mymodule")      # frames in your code
devtools_flamegraph(run_id)                                # all thread stacks as a graph
```

## Debug a live exe

```
devtools_run(suite="cdb", tool="stacks", binary="C:/path/app.exe", args=["--flag"])
```

(`cdb -g -G` runs to the end / through the initial breakpoint, then dumps stacks.)

## Symbols

Set `_NT_SYMBOL_PATH` so frames resolve to `module!function` instead of raw
addresses, e.g.:
```
SRV*C:\symbols*https://msdl.microsoft.com/download/symbols
```
plus the folder holding your app's PDBs. Without symbols, backtraces are just
offsets.

## Reading the output

- **`EXCEPTION_CODE` `c0000005`** = access violation (null/dangling pointer);
  `c00000fd` = stack overflow.
- The faulting thread is the one whose top frame matches `SYMBOL_NAME`, and its
  frames are shown first.
- All-thread `stacks` + `devtools_flamegraph` makes a deadlock obvious: multiple
  threads parked in the same lock path.

## Notes

- Batch mode covers crash/hang triage and dumps. **Interactive step-through** on
  Windows (breakpoints, stepping) is a planned follow-up (a ConPTY session
  mirroring the LLDB `debug_*` tools).
- For step-through on macOS/Linux today, use the LLDB `debug_start`/`debug` tools.
  Overall workflow: [[devtools-mcp-usage]].

Attribution

UgbotUgbot
View sourceSee grades on GitHubMore from Ugbot →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →