Borrowing it
Nothing to install: this file belongs to glslang/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.
curl -O https://raw.githubusercontent.com/glslang/windbg-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/glslang/windbg-mcpWrote 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.
[](https://agentmods.dev/instructions/glslang/windbg-mcp/claude-md)<a href="https://agentmods.dev/instructions/glslang/windbg-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/glslang/windbg-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.03211 | $0.03211 |
| Opus 5 | $0.01605 | $0.01605 |
| Sonnet 5 | $0.00642 | $0.00642 |
| Haiku 4.5 | $0.00321 | $0.00321 |
Grade A, and why
windbg-mcp CLAUDE.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repo. README.md is the map — it carries the tool table
and links out to one document per topic under docs/ (architecture.md, sessions.md,
tool-surface.md, structured-results.md, …); this file covers the non-obvious operational
workflows.
Most of that guidance is not in this file, and that is deliberate. What every session needs is
here; what only a part of the tree needs is a path-scoped rule under .claude/rules/, loaded when
Claude reads a file it covers; what is a procedure is a skill under .claude/skills/, whose body
costs nothing until it is invoked. Where the rest of it lives below is the index of both. Add to
this file only what a session touching none of those files still has to know — it is loaded in
full, every time, and length here is paid for by every other instruction competing with it.
What this is
windbg-mcp is a Rust MCP server (stdio, rmcp) exposing WinDbg/DbgEng for live user-mode,
kernel, crash-dump, and Time Travel Debugging (TTD) work. The low-level DbgEng bindings come from
the sibling crate dbgscope (a path/git dependency we grow
ourselves — do not add third-party DbgEng crates).
A new DbgEng primitive is a typed dbgscope method, returning Result<_, DbgEngError> rather
than panic!/.expect, never the execute text hatch. It is here rather than in
.claude/rules/cargo-and-dependencies.md with the rest of the dbgscope material because it binds a
Rust-only change, which loads that rule never — it is scoped to the manifests and build.rs.
The binary has two roles. Started normally it is the supervisor: MCP on stdio, no DbgEng.
Re-executed with --engine-worker it owns exactly one debug session, because dbgeng.dll holds one
debuggee session per process. Key source: src/engine.rs (the supervisor — session registry,
worker supervision, routing), src/worker.rs (the child process and the engine thread inside it),
src/proto.rs (the wire protocol between them), src/server.rs (the MCP tools),
src/kdconn.rs (KDNET connection profiles and the redacting Connection type), src/ttd.rs,
src/main.rs (role selection).
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.
- today Changed · -1,766 lines · -33,524 tokens per session 883da8ae8b5d
- yesterday Changed · +37 lines · +668 tokens per session e60adb2c3b1f
- 2d ago Changed · +143 lines · +2,839 tokens per session e71555f494a9
- 6d ago First seen · 1,754 lines · 33,228 tokens per session scan A 3e94378fc2b6
windbg-mcp CLAUDE.md is an instructions file published in the GitHub repository glslang/windbg-mcp (9 stars, last pushed yesterday), licensed MIT. It adds 3,211 tokens to every session, about $0.0161 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 2026-08-31.
Other instructions, from other repositories
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.
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.
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).
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).
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.
spec-kit AGENTS.md
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.