debug-that CLAUDE.md

Project instructions for debug-that, a command-line debugger that lets AI agents inspect and control running Node.js, Bun, and native programs.

In plain words
What is it for?
Understanding, changing, testing, and troubleshooting the debug-that codebase.
Why use it?
They give an agent the project layout, technology choices, commands, and validation rules needed to work on the debugger without first piecing together its structure.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/theodo-group/debug-that/claude-md
Clone the repo
git clone --depth 1 https://github.com/theodo-group/debug-that
Per session 806 This file is loaded in full into every session.
When invoked 806 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00806 $0.00806
Opus 5 $0.00403 $0.00403
Sonnet 5 $0.00161 $0.00161
Haiku 4.5 $0.00081 $0.00081

Measured 3d ago against content hash 1fbc6f378c66, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

debug-that 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.

CLAUDE.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

debug-that — Debugger CLI for AI Agents

Project Overview

CLI debugger built with Bun, optimized for AI agent consumption. Supports Node.js (CDP), Bun (JSC/WebKit), and native code via LLDB (DAP).

Tech Stack

  • Runtime: Bun
  • Language: TypeScript
  • Linting/Formatting: Biome
  • Testing: bun:test
  • Validation: Zod v4 (mini)
  • Dependencies: Minimal — leverage Bun built-ins (WebSocket, test runner, file I/O)

Project Structure

src/
  cli/          # CLI argument parsing, command routing, flag utilities
  session/      # Shared session abstractions
    session.ts    # Session interface + SessionCapabilities
    base-session.ts # BaseSession abstract class (shared state, refs, console)
    types.ts      # Shared types (PauseInfo, StateSnapshot, ConsoleMessage, etc.)
    factory.ts    # createSession() + isDapRuntime()
  daemon/       # Background daemon process, Unix socket server
  cdp/          # Chrome DevTools Protocol (Node.js / Bun)
    session.ts    # CdpSession (extends BaseSession)
    session-*.ts  # CDP method modules (breakpoints, execution, inspection, etc.)
    dialect.ts    # CdpDialect interface (V8 vs JSC strategy)
    adapters/     # NodeAdapter, BunAdapter (CdpDialect implementations)
    client.ts     # CdpClient WebSocket wrapper
  dap/          # Debug Adapter Protocol (LLDB, Python, etc.)
    session.ts    # DapSession (extends BaseSession)
    client.ts     # DapClient stdin/stdout wrapper
  refs/         # @ref system (mapping short refs to V8 IDs)
  formatter/    # Output formatting (variables, source, stack traces)
  commands/     # Command implementations (break, step, eval, etc.)
  protocol/     # CLI-to-daemon JSON protocol types
  sourcemap/    # Source map resolution
  util/         # Shared utilities (escapeRegex, etc.)
  constants.ts  # Centralized timeout/limit constants
tests/
  unit/         # Unit tests
  integration/  # Integration tests (node/, bun/, lldb/, shared/)
  fixtures/     # Test fixture scripts

Read the full file on GitHub · 67 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. 3d ago First seen · 67 lines · 806 tokens per session scan A 1fbc6f378c66

Subscribe to this mod's changes

debug-that CLAUDE.md is an instructions file published in the GitHub repository theodo-group/debug-that (157 stars, last pushed 3mo ago), licensed MIT. It adds 806 tokens to every session, about $0.0040 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 2026-08-30.