Use it when building or operating AI-assisted debugging tools, setting breakpoints, inspecting runtime state, stepping through code, or using a launch.json configuration.

It explains how debugging works when a program must be paused before its variables, stack, or next line can be inspected.

How ai-debugger-inc/aidb configures Claude Code

Q: What is aidb CLAUDE.md?

Project guidance for aidb, a Python API that lets AI systems inspect and control live debugging sessions through the Debug Adapter Protocol (DAP), the standard connection used by debuggers and development tools.

Reuse

Borrowing it

Nothing to install: this file belongs to ai-debugger-inc/aidb. 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/ai-debugger-inc/aidb/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/ai-debugger-inc/aidb

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/ai-debugger-inc/aidb/claude-md/github.svg)](https://agentmods.dev/instructions/ai-debugger-inc/aidb/claude-md)

Your own site

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

Per session 1,596 This file is loaded in full into every session.

When invoked 1,596 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.

Model	Per session	Once invoked
Fable 5.1	$0.01596	$0.01596
Opus 5.5	$0.00638	$0.00638
Sonnet 5.5	$0.00319	$0.00319
Haiku 4.5	$0.00160	$0.00160

Measured 2mo ago against content hash fa9eb7093e66, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aidb 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 2mo 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.

CLAUDE.md · 137 lines

How it starts

The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Debugger (aidb) - Claude Code Context

Project Overview

AI Debugger (aidb) is a lightweight, language-agnostic Python API that enables AI systems to programmatically control and introspect live debugging sessions through the Debug Adapter Protocol (DAP). It serves as an ideal Model Context Protocol (MCP) tool for AI-assisted debugging workflows.

The debugger interface is intended to function at a human cadence, not a typical, super-fast API. For example:

If you want to inspect runtime state in a program that executes quickly, you must set a breakpoint when you start the debug session. If you need to set a conditional breakpoint, you must do so before starting the debug session.
If you want to perform introspection on the state, you must execute the operations on a paused program that fetch whatever is needed, e.g. local variables or a stack frame.
If you want to advance a line, that is a single operation. To skip multiple lines, you must execute multiple operations, just like a human using a debugger.
If you want to use your launch.json file, you can.

User Profile: Developers building debugging tools + AI agents using MCP for code debugging workflows.

Project Components

Core Debugger: aidb/ - Language-agnostic debugging API, adapters (Python/JavaScript/Java), session management MCP Integration: aidb_mcp/ - MCP server exposing 12 debugging tools to AI agents Developer Tools: aidb_cli/ - CLI for testing orchestration, Docker management, adapter builds Shared Libraries: aidb_common/ (config, validation, paths), aidb_logging/ (structured logging)

Architecture Overview

AI Debugger is built on a layered architecture that provides language-agnostic debugging capabilities:

MCP Layer (aidb_mcp/): Model Context Protocol server exposing 12 agent-optimized debugging tools
Service Layer (aidb/service/): Stateless debugging operations via DebugService with sub-services for execution, stepping, breakpoints, variables, and stack inspection
Session Layer (aidb/session/): Core session orchestration, state management, and lifecycle control
Adapter Layer (aidb/adapters/): Language-specific debug adapters (Python, JavaScript, Java)
DAP Client Layer (aidb/dap/client/): Debug Adapter Protocol client implementation
Protocol Layer (aidb/dap/protocol/): Fully-typed DAP specification (authoritative reference)

Read the full file on GitHub · 137 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.

2mo ago First seen · 137 lines · 1,596 tokens per session scan A fa9eb7093e66

Subscribe to this mod's changes

aidb CLAUDE.md is an instructions file published in the GitHub repository ai-debugger-inc/aidb (21 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 1,596 tokens to every session, about $0.0064 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 2026-08-30.

Debugging LLM Languages Python ai ai-agents developer-tools llms mcp

aidb CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aidb CLAUDE.mdai-debugger-inc/aidb	Instructions file	21	5mo ago	Apache-2.0	A	1,596	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

aidb: Instructions file for Claude Code