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/wallter/smart-xdebug-mcp/claude-mdgit clone --depth 1 https://github.com/wallter/smart-xdebug-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/wallter/smart-xdebug-mcp/claude-md)<a href="https://agentmods.dev/instructions/wallter/smart-xdebug-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/wallter/smart-xdebug-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 | $0.00909 | $0.00909 |
| Opus 5 | $0.00454 | $0.00454 |
| Sonnet 5 | $0.00182 | $0.00182 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
smart-xdebug-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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
Smart XDebug MCP is an MCP (Model Context Protocol) server that bridges XDebug's DBGp protocol with Claude, enabling AI-powered PHP debugging. The philosophy is "Pull, Don't Push" - the AI requests specific data slices rather than receiving full state dumps.
Commands
# Build
npm run build # Compile TypeScript to dist/
# Development
npm run dev # Watch mode compilation
npm run typecheck # Type checking without emit
# Testing
npm test # Run all tests
npm run test:watch # Watch mode
npm run test:coverage # With coverage (80% threshold)
# Run a single test file
npx vitest run tests/path-mapper.test.ts
# Test app (Docker required)
make test-app-setup # First-time setup (installs Laravel, starts containers)
make test-app-up # Start containers
make test-app-down # Stop containers
Architecture
src/
├── index.ts # MCP server entry point (stdio transport)
├── config.ts # Zod-validated configuration (env vars)
├── errors.ts # Error hierarchy (XDebugMcpError base class)
├── types/index.ts # Core TypeScript types
├── tools/ # MCP tool handlers
│ ├── index.ts # Tool definitions + handleToolCall router
│ ├── start-session.ts # start_debug_session
│ ├── set-breakpoint.ts # set_breakpoint
│ ├── inspect-variable.ts # inspect_variable (JSONPath filtering)
│ ├── control-execution.ts # control_execution (step/continue/stop)
│ ├── get-status.ts # get_session_status
│ └── query-history.ts # query_history (time-travel)
├── debug/
│ ├── session-manager.ts # Central coordinator (singleton per server)
│ ├── dbgp-connection.ts # DBGp protocol over TCP
│ ├── path-mapper.ts # Host↔container path translation
│ └── session-recorder.ts # SQLite history for time-travel
└── utils/
└── logger.ts # Structured JSON logging
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.
- 3d ago First seen · 88 lines · 909 tokens per session scan A 861fcd6ffebf
smart-xdebug-mcp CLAUDE.md is an instructions file published in the GitHub repository wallter/smart-xdebug-mcp (1 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 909 tokens to every session, about $0.0045 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
DebugMCP AGENTS.md
AGENTS.md instructions for microsoft/DebugMCP, covering agent guidelines for debugmcp, project overview, architecture, key components and documentation maintenance.
dotnet-dump-mcp AGENTS.md
Instructions for frankbolero/dotnet-dump-mcp, covering claude.md, project summary, build, test, and development commands, core development and build the solution.
karellen-rr-mcp CLAUDE.md
Instructions for karellen/karellen-rr-mcp, covering claude.md, project, build & test, lint and architecture.
pwa-debug-layer CLAUDE.md
Claude Code instructions for aryanduntley/pwa-debug-layer: AIMFP MODE ACTIVE — MANDATORY BEHAVIORAL RULES.
codex-blackbox AGENTS.md
Instructions for softcane/codex-blackbox, covering codex blackbox agent instructions, product boundary, implementation map, worktree rules and codex routing.
dotnet-dump-mcp CLAUDE.md
Instructions for frankbolero/dotnet-dump-mcp, a project described as: 🤖 An AI-native CLI Tool and MCP server for .NET memory dump investigations. Leverage LLMs (Claude/Gemini) to analyze heaps, threads, and exceptions using natural language. Built with ClrMD, token-efficient paging, and Docker support for…