Nietzschian Debugger CLI

Nietzschian Debugger is a question-based debugging CLI with per-run model selection; the next invocation has its own setting.

  • 552 ★ on the repository
  • Last commit
  • MIT
CLI

Broad access

Why this level

  • `nietzschian predict` executes functions from the selected Python module with user permissions.
All reasons and checks

dilawarshafiq/nietzschian-debugger

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add cli/nietzschian-debugger

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • `nietzschian predict` executes functions from the selected Python module with user permissions.

This is third-party code. Review the repository files before installing.

What it does

Nietzschian Debugger is a developer CLI that investigates a bug through questions. It asks users to distinguish observations from assumptions, clarify conditions and test a disputed hypothesis. Instead of an automatic patch, users get direction for their own diagnosis. A source path or uncommitted `diff` can provide context. Models are selected per invocation, including hosted providers and Ollama. A separate `predict` mode asks users to anticipate their own function’s result and executes it; `roast` reviews a file in a deliberately sharp style.

Who it is for. Developers testing their own bug hypotheses and exploring code behavior through a guided discussion.

Good fit when

  • A developer separates an observed failure from an assumed cause.
  • The current Git diff is included in the discussion.
  • A user practices predicting a trusted function’s result.
  • An authorized local model is selected for private code analysis.

Not a fit when

  • You need an automatic patch without developer involvement.
  • A confrontational question style is unsuitable.
  • Functions in the selected Python module must not be executed.

Example request

Help test my bug hypothesis through questions without executing code or editing files.

Limitations

Python 3.10 or later and a configured model are required; Ollama runs separately. Hosted providers receive submitted source and diffs, so choose authorized context only. Predict executes your functions in a timed subprocess, which is not a complete sandbox; use trusted modules with restricted permissions. Wording is deliberately confrontational, so try the demo before deciding whether this format suits you or a learner.

How to disable. Exit the session and uninstall the Python package. Inspect saved conversations and Markdown exports separately.

FAQ

Is there a demo without credentials?

Yes. Run `nietzschian demo`.

How do I include uncommitted changes?

Add `--diff` to `nietzschian debug` to include uncommitted Git changes. Supply the bug description and include only authorized project context.

How do I choose Ollama?

Start Ollama and load the required model. Pass `--model ollama:llama3.1` for the documented example, and select it again on the next invocation.

How do I export a conversation?

`nietzschian share -o run.md` creates Markdown output.

Should I use the old npm package?

The current version is Python-based; the previous npx build is deprecated.

Discussion

No questions or reviews yet.

CLI tools

The dbg debugger CLI for AI agents: breakpoints, steps and variables through short @ref handles instead of print debugging

CLIExtended access159Repository stars

A debugging skill built on hypotheses: the agent adds logs, reproduces the bug itself, tests its guesses and cleans up

SkillExtended access120Repository stars

A debugging tool for Claude Code that reads the session logs already saved on disk and shows exact file paths, diffs, model thinking and a category-by-category

CLIExtended access4KRepository stars

An MCP server for the Node.js debugger: breakpoints, stepping, variable inspection and expression evaluation at a pause

MCP serverBroad access350Repository stars

A CLI turns Git changes into a guided code walkthrough with questions and explanations written by your existing agent

CLIExtended access363Repository stars

Methods for an agent in one CLI: comparing options, solving problems and changing code in steps, 20 slash commands in all.

CLIExtended access125Repository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialAuthenticationRepository starsMain difference
Nietzschian Debugger (this card)no552
Node.js Debugger MCPnonot required350controls Node.js execution through an inspector; Nietzschian Debugger uses questions to test developer assumptions
Gripno373A CLI asks questions about a Git diff before push and uses a chosen model to assess how well the developer understands the change.

README in short

Hosted providers and Ollama use the same model-selection option. The demo needs no key, while real discussions require access to the selected model.

README badge

Report a problem

Foxx AINietzschian Debugger
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.