windbg-mcp: Instructions file for Codex

AGENTS.md

windbg-mcp AGENTS.md is an instructions file for Codex, OpenCode from kanren3/windbg-mcp. It costs 3,330 tokens per session, scanned A, original, MIT.

A Windows-only debugging server that lets an AI assistant work with WinDbg, a Microsoft tool for investigating running programs and crash dumps.

In plain words
What is it for?
Use it for crash-dump analysis, live process debugging, and kernel debugging on Windows.
Why use it?
It removes the need to manually drive separate user-mode and kernel-mode debugging tools while examining failures or live processes.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is kanren3/windbg-mcp's own configuration. It tells Codex and OpenCode how to work on windbg-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything windbg-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to kanren3/windbg-mcp. 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/kanren3/windbg-mcp/master/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/kanren3/windbg-mcp

Made for: Codex, OpenCode.

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 windbg-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/kanren3/windbg-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/kanren3/windbg-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/kanren3/windbg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kanren3/windbg-mcp/agents-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.

agentmods 80×15 button for windbg-mcp AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/kanren3/windbg-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/kanren3/windbg-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3,330 This file is loaded in full into every session.
When invoked 3,330 The same file — it is already loaded in full.
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 $0.03330 $0.03330
Opus 5.5 $0.01332 $0.01332
Sonnet 5.5 $0.00666 $0.00666
Haiku 4.5 $0.00333 $0.00333

Measured 17d ago against content hash a5f078526780, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

windbg-mcp AGENTS.md 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 17d 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.

AGENTS.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

General Principles

  • Read before you change. Before modifying code, read the relevant files and existing implementations in the same module; prefer reuse.
  • Simple, but well designed. Avoid over-engineering; do not add abstractions or complexity for hypothetical requirements. New dependencies must have clear benefits; prefer capabilities the project already has.
  • Low coupling, high readability. Keep module responsibilities clear and dependencies simple; use accurate naming and appropriate comments so code is easy to understand and review.
  • Natural comments. Express intent primarily through naming and structure; comments supplement only the rationale, constraints, and special logic that the code itself cannot express. Write comments as final content; do not repeat the code, describe change history, comparisons, or the implementation process, or leave awkward implementation notes.
  • Implement based on facts. For external behavior involving APIs, frameworks, libraries, or protocols, rely primarily on official documentation, source code, specifications, or existing tests. When these are insufficient to determine behavior that affects the implementation, do not assume — pause and ask. Existing project code, tests, and explicit conventions are also reliable sources.
  • Confirm the problem exists first. Before fixing a bug, understand the relevant code, check existing tests, and reproduce the problem when conditions allow, while confirming the expected behavior has a reliable basis. If reproduction is impossible due to environment, timing, or other constraints, base your judgment on code, tests, logs, documentation, or other reliable evidence — never modify on guesswork. If the problem is confirmed not to exist, do not change code for the sake of changing it.
  • Minimal changes. Modify only what is necessary to solve the current problem; avoid unrelated refactoring and drive-by optimizations. When changing behavior, also review comments, documentation, and examples directly affected by that behavior; update them only when they are outdated or contradict the new behavior.
  • One-directional constraints. When writing rules (including this file), state each rule once, in its clearest form; do not append a redundant restatement of its inverse.

Read the full file on GitHub · 140 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. 17d ago Changed · +37 lines · +1,297 tokens per session a5f078526780
  2. 1mo ago First seen · 103 lines · 2,033 tokens per session scan A d3612b50167b

Subscribe to this mod's changes

windbg-mcp AGENTS.md is an instructions file published in the GitHub repository kanren3/windbg-mcp (7 stars, last pushed 18d ago), licensed MIT. It adds 3,330 tokens to every session, about $0.0133 per session on Opus 5.5. 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 2026-08-31.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

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).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,461 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

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.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deno copilot-instructions.md

Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.

denoland/deno · 3,077 tokens