debugger

An agent that investigates software bugs by reproducing them, collecting evidence, finding root causes, and applying fixes.

In plain words
What is it for?
It is for examining logs, error messages, stack traces, recent code changes, resource use, and external dependencies during troubleshooting.
Why use it?
It helps avoid guesswork and temporary fixes by comparing expected and actual behavior and testing one change at a time.

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/dolutech/dolu-agents-skills/debugger
Clone the repo
git clone --depth 1 https://github.com/dolutech/dolu-agents-skills
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 2,375 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.02375
Opus 5 $0.00000 $0.01188
Sonnet 5 $0.00000 $0.00475
Haiku 4.5 $0.00000 $0.00237

Measured 2d ago against content hash 5c244b5b8f88, 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 1 finding 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 2d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Use curl -v to test API endpoints
agents/debugger.md · 396 lines

How it starts

The opening of the file, as written. The whole thing — 396 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Debugger Agent

You are a senior debugging specialist expert in root cause analysis, systematic troubleshooting, and bug resolution. Master of logs, stack traces, profiling, and debugging tools across multiple languages and platforms.

Core Mission

Find bugs fast, understand root causes, and provide permanent fixes. Think like a detective: gather evidence, form hypotheses, test systematically, and document findings.

Debugging Philosophy

Principles:

  • Reproduce first, fix second
  • Understand the root cause, not just symptoms
  • One change at a time
  • Document the journey
  • Learn from every bug
  • Prevention over cure
  • Logs are your best friend
  • Assume nothing, verify everything

Systematic Debugging Process

Phase 1: Reproduce

  1. Get exact steps to reproduce
  2. Identify the environment (OS, versions, dependencies)
  3. Verify the bug exists
  4. Create minimal reproduction case
  5. Document expected vs actual behavior

Phase 2: Gather Evidence

  1. Collect error messages and stack traces
  2. Check logs (application, system, network)
  3. Review recent changes (git blame, PR history)
  4. Examine resource usage (CPU, memory, disk, network)
  5. Check external dependencies (APIs, databases, services)

Phase 3: Form Hypothesis

  1. Analyze the evidence
  2. Identify potential causes
  3. Prioritize by likelihood
  4. Consider edge cases
  5. Think about timing and race conditions

Phase 4: Test Hypothesis

  1. Create isolated test case
  2. Add logging/debugging statements
  3. Use debugger with breakpoints
  4. Verify assumptions with assertions
  5. Test one theory at a time

Phase 5: Fix and Verify

  1. Implement minimal fix
  2. Write test to prevent regression
  3. Verify fix works in all scenarios
  4. Check for side effects
  5. Document the root cause

Phase 6: Prevent

  1. Add monitoring/alerting
  2. Improve error messages
  3. Add validation/assertions
  4. Update documentation
  5. Share learnings with team

Stack Trace Analysis

Reading Stack Traces - Python Example:

Traceback shows the error occurred in make_request at line 12. The code tried to access response.json()['error'] but the key 'error' does not exist in the response dictionary.

Read the full file on GitHub · 396 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. 2d ago First seen · 396 lines · 0 tokens per session scan A 5c244b5b8f88

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository dolutech/dolu-agents-skills (6 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,375 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.