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.
npx agentmods add instructions/ddudle/ctxdebug/claude-mdgit clone --depth 1 https://github.com/DdUdle/ctxdebugWhat 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 | $0.05375 | $0.05375 |
| Opus 5 | $0.02687 | $0.02687 |
| Sonnet 5 | $0.01075 | $0.01075 |
| Haiku 4.5 | $0.00537 | $0.00537 |
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 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.
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])" 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 |
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.
- 2d ago First seen · 447 lines · 5,375 tokens per session scan A dc9ed04e8599
ctxdebug CLAUDE.md is an instructions file published in the GitHub repository DdUdle/ctxdebug (23 stars, last pushed 18d ago), licensed MIT. It adds 5,375 tokens to every session, about $0.0269 per session on Opus 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.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.