agent-debugger

agent-debugger is an agent for coding agents from lucafusarbassini/research-automation. It costs 0 tokens per session (82 once invoked), scanned A, original, MIT.

A debugging agent for machine-learning training. It checks whether training code, data, or model design is causing failures, including accidental information leakage.

In plain words
What is it for?
Use it to inspect gradient flow, data loading, NaN or infinite values, model architecture, and anti-cheating tests with Python, source inspection, and shell scripts.
Why use it?
It helps separate coding and data problems from expected training behavior, while checking that the model is not receiving answers it should not see.

Agent

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 agents/lucafusarbassini/research-automation/agent-debugger
Clone the repo
git clone --depth 1 https://github.com/lucafusarbassini/research-automation

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.

agentmods badge for agent-debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/lucafusarbassini/research-automation/agent-debugger.svg)](https://agentmods.dev/agents/lucafusarbassini/research-automation/agent-debugger)
Your own site
<a href="https://agentmods.dev/agents/lucafusarbassini/research-automation/agent-debugger"><img src="https://agentmods.dev/badge/agents/lucafusarbassini/research-automation/agent-debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 82 The whole file, excluding the scripts and references it only reads on demand.
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 5.1 $0.00000 $0.00082
Opus 5 $0.00000 $0.00041
Sonnet 5 $0.00000 $0.00016
Haiku 4.5 $0.00000 $0.00008

Measured 5d ago against content hash 48915aff8681, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-debugger 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 5d 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-overnight-toolkit/agents/agent-debugger.md · 17 lines

What it actually says

Agent: Debugger

Diagnoses training failures, checks for bugs and information leakage.

Responsibilities

  • Check gradient flow
  • Verify data loading correctness
  • Test for information leakage
  • Diagnose NaN/inf issues
  • Validate model architecture
  • Run anti-cheating baselines

Tools

  • Python for debugging scripts
  • Read for source code inspection
  • Bash for running diagnostic scripts
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. 5d ago First seen · 17 lines · 0 tokens per session scan A 48915aff8681

Subscribe to this mod's changes

agent-debugger is an agent published in the GitHub repository lucafusarbassini/research-automation (5 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 82 tokens. 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.

Related

Other agents, from other repositories

Prompt Builder

Expert prompt engineering and validation system for creating high-quality prompts - Brought to you by microsoft/edge-ai.

github/awesome-copilot · 24 tokens

Research Harness Engineer

Research harness engineer for experiment campaigns: builds evaluation harnesses that are hard to fool, then keeps every reported number honest - null models first, calibration/held-out separation, baseline reproduction before improvement claims, paired error bars, and guards verified by deliberate breakage.

github/awesome-copilot · 56 tokens

AGENTS

In-depth tutorials on LLMs, RAGs and real-world AI agent applications.

patchy631/ai-engineering-hub · 0 tokens

apple-neural-performance-expert

Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…

FluidInference/FluidAudio · 0 tokens

fit

Selects algorithms, tunes hyperparameters, and builds reproducible training pipelines from baseline to production. Use when choosing a model architecture, designing a tuning strategy, or auditing training code for leakage and reproducibility. Trigger with "design training pipeline", "tune model hyperparameters".

jeremylongshore/tons-of-skills-marketplace · 57 tokens

algorithm-expert

RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.

redai-infra/Relax · 37 tokens