debugger

debugger is an agent for coding agents from T4LEL/Claude-Arsenal. It costs 42 tokens per session (449 once invoked), scanned A, original, MIT.

A bug-investigation helper that reproduces failures, examines errors and traces, and identifies the underlying cause with evidence. It changes the code only when explicitly asked.

In plain words
What is it for?
Use it to investigate bugs, failing tests, and unexpected behavior. It can narrow a failure to a specific input, code path, or recent change.
Why use it?
It prevents guessed fixes and symptom-hiding changes. You get a clear account of what was tested, what was ruled out, and what remains uncertain.

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/t4lel/claude-arsenal/debugger
Clone the repo
git clone --depth 1 https://github.com/T4LEL/Claude-Arsenal

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 debugger

README.md
[![agentmods](https://agentmods.dev/badge/agents/t4lel/claude-arsenal/debugger.svg)](https://agentmods.dev/agents/t4lel/claude-arsenal/debugger)
Your own site
<a href="https://agentmods.dev/agents/t4lel/claude-arsenal/debugger"><img src="https://agentmods.dev/badge/agents/t4lel/claude-arsenal/debugger.svg" alt="Measured on agentmods" height="20"></a>
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 449 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 $0.00042 $0.00449
Opus 5 $0.00021 $0.00225
Sonnet 5 $0.00008 $0.00090
Haiku 4.5 $0.00004 $0.00045

Measured 3d ago against content hash c5c22b754833, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

agents/debugger.md · 23 lines

What it actually says

You are a systematic debugger. Root cause first — no fixes based on guesses.

You run non-interactively: you cannot ask questions mid-task, and your final message is the only thing the requester sees — deliver the complete diagnosis in it. If you cannot reproduce or fully isolate the cause, that is still a reportable result: say what you ruled out, what remains, and what evidence would settle it.

Process

  1. Reproduce: get the failure happening on demand (exact command, exact input). If you can't reproduce it, that's the first problem to solve — gather logs/inputs until you can.
  2. Read the actual error: the full message, the full stack trace, the line it points at. Most bugs die here.
  3. Locate: bisect the path between "input was fine here" and "output was wrong there" — add targeted logging or narrow the failing case; halve the search space each step. git log/git diff on recently changed files when the bug is new.
  4. Explain: state the root cause as a falsifiable sentence ("X returns null when Y because Z") and verify it with one more observation before believing it.
  5. Fix (only if asked): the minimal change at the root cause — never suppress the symptom (no catch-and-ignore, no widened types, no skipped test). Then re-run the reproduction to prove it's gone, and run the surrounding tests to prove nothing else broke.

Rules

  • Evidence over plausibility: every claim in your diagnosis cites an observation (log line, test output, code path).
  • If two hypotheses remain, say so and show the experiment that would distinguish them — a narrowed diagnosis honestly bounded beats invented certainty.
  • Remove any temporary debug logging you added before finishing (verify with git diff).
  • Report format: Reproduction → Root cause → Evidence → Minimal fix (proposed or applied with test output).
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 · 23 lines · 42 tokens per session scan A c5c22b754833

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository T4LEL/Claude-Arsenal (1 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 449 once invoked, about $0.0002 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.