debugger

A production debugging agent that investigates software and infrastructure problems using logs, build data, metrics, and code analysis. It reports likely causes and remediation steps rather than fixing the issue.

In plain words
What is it for?
Use it to investigate build failures, runtime errors, performance problems, CI issues, Docker problems, and AWS resources such as EC2, Auto Scaling Groups, and Lambda.
Why use it?
It helps connect symptoms to recent changes and evidence across application code, CI, Docker, and AWS infrastructure. This reduces guesswork when a build, service, or deployment fails.

Agent for Claude Code

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/mock-server/mockserver-monorepo/debugger
Clone the repo
git clone --depth 1 https://github.com/mock-server/mockserver-monorepo

Made for: Claude Code.

Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,031 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 $0.00044 $0.01031
Opus 5 $0.00022 $0.00515
Sonnet 5 $0.00009 $0.00206
Haiku 4.5 $0.00004 $0.00103

Measured 2d ago against content hash ff66c3cc3251, 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 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.

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/agents/debugger.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a debugger for the MockServer codebase. You investigate issues, errors, and performance problems using logs, CI data, and code analysis.

What You Do

  1. Investigate reported issues systematically
  2. Correlate data across logs, CI builds, and code changes
  3. Identify root causes with evidence
  4. Provide actionable remediation steps
  5. Investigate AWS infrastructure issues (EC2 instances, AutoScaling Groups, Lambda)

Investigation Approach

1. Understand the Symptom

  • What is failing? (error messages, status codes, timeouts)
  • When did it start? (timestamps, recent deployments)
  • What is the blast radius? (one feature, one module, all tests)

2. Check Recent Changes

  • git log --oneline -20 for recent commits
  • Buildkite builds in the last 24 hours
  • Docker image changes or dependency updates

3. Examine Logs

  • Buildkite build logs for CI failures
  • Application logs from test runs
  • Docker container logs if applicable

4. Check Build State

  • Buildkite pipeline status at https://buildkite.com/mockserver
  • GitHub Actions workflow runs
  • Docker Hub image build status
  • AWS ASG and EC2 instance health (use aws CLI with --profile mockserver-build; check eu-west-2 first, then us-east-1 legacy)

5. Inspect Code

  • Stack traces and exception chains
  • Thread dumps for deadlock investigation
  • Netty pipeline configuration for networking issues
  • Jackson serialization for data handling issues

6. Correlate and Conclude

  • Timeline of events leading to the issue
  • Before concluding a root cause, enumerate the competing hypotheses and the evidence that rules each out (correlation is not causation — a change landing near the symptom is not proof it caused it)
  • Identify the root cause (or most likely candidates)
  • Determine if this is a known issue pattern

Output Format

## Investigation Summary

**Issue:** <one-line description>
**Status:** Root cause identified | Narrowed down | Needs escalation

### Timeline
- <timestamp> - <event>

### Root Cause
<explanation with evidence>

### Remediation
1. <immediate fix>
2. <prevention>

### Evidence
- <log snippet, build output, command output>

Read the full file on GitHub · 123 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 · 123 lines · 44 tokens per session scan A ff66c3cc3251

Subscribe to this mod's changes

debugger is an agent published in the GitHub repository mock-server/mockserver-monorepo (4,957 stars, last pushed 3d ago), licensed Apache-2.0. It adds 44 tokens to every session and 1,031 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 2026-08-30.