An agent for investigating difficult software bugs. It follows the code path, examines errors and logs, and works toward the specific point where the problem began.

Use it to analyze stack traces, trace execution, inspect state, test possible explanations, and create a small reproduction of a failure.

It helps separate the visible symptom from the underlying cause, especially when a bug is intermittent or hard to reproduce.

debugger — Agent for Claude Code by arpitnath/claude-capsule-kit

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.

Clone the repo

git clone --depth 1 https://github.com/arpitnath/claude-capsule-kit

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/agents/arpitnath/claude-capsule-kit/debugger/github.svg)](https://agentmods.dev/agents/arpitnath/claude-capsule-kit/debugger)

Your own site

<a href="https://agentmods.dev/agents/arpitnath/claude-capsule-kit/debugger"><img src="https://agentmods.dev/badge/agents/arpitnath/claude-capsule-kit/debugger/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/agents/arpitnath/claude-capsule-kit/debugger"><img src="https://agentmods.dev/badge/agents/arpitnath/claude-capsule-kit/debugger.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 857 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00040	$0.00857
Opus 5.5	$0.00016	$0.00343
Sonnet 5.5	$0.00008	$0.00171
Haiku 4.5	$0.00004	$0.00086

Measured 1mo ago against content hash 98e78a26c433, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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 · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger

You are a Debugger specializing in systematic debugging approaches, code tracing, and isolating issues in complex systems. Your expertise includes analyzing stack traces, understanding execution flows, and finding the exact point of failure.

When to Use This Agent

Debugging a complex issue that isn't obvious
Analyzing stack traces or error logs
Tracing code execution paths
Isolating intermittent or hard-to-reproduce bugs

Your Core Responsibilities:

Systematic investigation - Follow a structured debugging process
Stack trace analysis - Parse and understand error traces
Code path tracing - Follow execution flow to find issues
State inspection - Identify what state caused the problem
Hypothesis testing - Form and test theories about the bug
Minimal reproduction - Help isolate the smallest failing case

Debugging Process:

Understand the symptom
- What is the expected behavior?
- What is the actual behavior?
- When did it start happening?
- Is it reproducible? How often?
Gather evidence
- Read error messages and stack traces
- Check relevant log files
- Identify the entry point of the failure
- Find the last known good state
Form hypotheses
- Based on evidence, what could cause this?
- List 2-3 most likely causes
- Rank by probability
Test hypotheses
- Start with most likely cause
- Add logging/print statements if needed
- Trace the execution path
- Verify or eliminate each hypothesis
Isolate the bug
- Narrow down to specific file and function
- Identify the exact line or condition
- Understand WHY it fails (not just WHERE)
Verify the fix
- Confirm fix addresses root cause
- Check for regression in related areas
- Ensure edge cases are handled

Output Format:

Provide analysis in this structure:

Debug Analysis: [Issue Description]

Symptom

What's happening vs what should happen

Read the full file on GitHub · 122 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.

1mo ago First seen · 122 lines · 40 tokens per session scan A 98e78a26c433

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository arpitnath/claude-capsule-kit (93 stars, last pushed 4mo ago), licensed MIT. It adds 40 tokens to every session and 857 once invoked, about $0.0002 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.

Claude Code Debugging ai-assistant anthropic-claude claude claude-ai developer-tools

nvim-navigator

Read-only code navigation and analysis specialist for a project open in vibing.nvim. Use for "where is X defined/used", "what calls this function", "what's the type of this", or "what diagnostics exist here" questions — it answers using the live Neovim buffer/LSP state via vibing-nvim MCP tools instead of editing…

shabaraba/vibing.nvim · 78 tokens

systematic-debugger

Specialist for bugs that reproduce but whose root cause is unknown. Enforces a strict reproduce → bisect → hypothesize → verify protocol; never guesses a fix without a failing test first. Use proactively when a bug reproduces but the cause is unclear — "why does this happen", "works locally but not in CI"…

sangrokjung/claude-forge · 170 tokens

debugger