What is ctxdebug CLAUDE.md?

Instructions for a system that connects AI assistants to Windows debugging and reverse-engineering tools such as WinDbg, IDA Pro, and x64dbg. Reverse engineering means examining compiled software to understand how it works.

Use them when adding debugger connections, changing MCP servers, working with Windows security research tools, or running the multi-debugger controller.

They explain the repository layout, language rules, and ways to start or extend its debugging servers, reducing setup mistakes when working across several tools.

How DdUdle/ctxdebug configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to DdUdle/ctxdebug. 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/DdUdle/ctxdebug/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/DdUdle/ctxdebug

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ddudle/ctxdebug/claude-md/github.svg)](https://agentmods.dev/instructions/ddudle/ctxdebug/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ddudle/ctxdebug/claude-md"><img src="https://agentmods.dev/badge/instructions/ddudle/ctxdebug/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ddudle/ctxdebug/claude-md"><img src="https://agentmods.dev/badge/instructions/ddudle/ctxdebug/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 5,434 This file is loaded in full into every session.

When invoked 5,434 The same file — it is already loaded in full.

Security scan A 2 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.

Model	Per session	Once invoked
Fable 5.1	$0.05434	$0.05434
Opus 5.5	$0.02174	$0.02174
Sonnet 5.5	$0.01087	$0.01087
Haiku 4.5	$0.00543	$0.00543

Measured 1mo ago against content hash c4cffb6cc9a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ctxdebug CLAUDE.md scanned grade A with 2 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

python -c "import urllib.request; print(urllib.request.urlopen('http://localhost:2022/api/v1/py', timeout=3))"

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

python -c "import subprocess; print(subprocess.run(['C:\\Program Files (x86)\\Windows Kits\\10\\Debuggers\\x64\\cdb.exe', '-version'], capture_output=True, text=True).stdout[:80])"

CLAUDE.md · 447 lines

How it starts

The opening of the file, as written. The whole thing — 447 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCO — Multi-debugger Controller Orchestrator

MCP server platform that connects WinDbg, IDA Pro 9.x, and x64dbg to Claude AI for AI-assisted reverse engineering and Windows security research.

Owner: Windows security researcher (heap exploitation, anti-debug). Language policy: Code and docs in English only.

Repository layout

C:\Users\dange\mcp\mco\
├── windbg_mcp.py            # WinDbg via cdb.exe subprocess. 70+ tools. PRODUCTION.
├── ida_mcp.py               # IDA Pro 9.x via HTTP REST (localhost:2022). 32+ tools.
├── ida_server_plugin.py     # Paste into IDA Python console to start HTTP server.
├── agent/                   # x64dbg MCP via named pipe
│   ├── __main__.py          # Entry: python -m agent --mcp
│   ├── core.py              # Shared debugging context (bridge, skills, state)
│   ├── bridge.py            # Named-pipe IPC to x64dbg C++ plugin
│   ├── mcp_server.py        # MCP server + 35+ tool definitions
│   └── plugins/
│       ├── x64dbg_plugin.cpp   # C++ plugin — compile with build_plugin.bat
│       └── build_plugin.bat    # MSVC build (produces mco_agent.dp64)
├── mco_orchestrator.py      # Cross-debugger meta-tools. 7 compound workflows.
├── mco_sessions.py          # SQLite session recorder/replayer. 13 tools.
├── mcp_config_example.json  # All MCP server configs with env vars
├── pyproject.toml           # Python package (x64dbg-mcp-agent)
├── sessions.db              # SQLite DB (auto-created by mco_sessions.py)
├── site/index.html          # Startup landing page
└── .windbg_mcp_breakpoints/ # Saved breakpoint sets (cmd files)

MCP servers — quick reference

Server name	File	Provides	Tool count
`windbg`	`windbg_mcp.py`	Crash dumps, heap, shadow stack, kernel	70+
`ida`	`ida_mcp.py`	Static analysis, decompile, rename, patches	32+
`x64dbg`	`agent/__main__.py`	Dynamic analysis, anti-debug bypass	35+
`mco`	`mco_orchestrator.py`	Cross-debugger compound workflows	7
`mco-sessions`	`mco_sessions.py`	Session recording, FTS search, export	13

Read the full file on GitHub · 447 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.

1mo ago Changed · +59 tokens per session c4cffb6cc9a7
2mo ago First seen · 447 lines · 5,375 tokens per session scan A dc9ed04e8599

Subscribe to this mod's changes

ctxdebug CLAUDE.md is an instructions file published in the GitHub repository DdUdle/ctxdebug (31 stars, last pushed 1mo ago), licensed MIT. It adds 5,434 tokens to every session, about $0.0217 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Debugging

ctxdebug CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ctxdebug CLAUDE.mdDdUdle/ctxdebug	Instructions file	31	1mo ago	MIT	A	5,434	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

ctxdebug: Instructions file for Claude Code