agentmods.dev

jdb-diagnostics

jdb-diagnostics is an agent for Claude Code from brunoborges/jdb-agentic-debugger. It costs 44 tokens per session (528 once invoked), scanned A, original, MIT.

An agent for collecting diagnostic snapshots from a running Java virtual machine, the software that runs Java programs, using JDB.

In plain words
What is it for?
It is for quick health checks on a running Java program whose debugging connection is enabled, including thread dumps, deadlock checks, and class listings.
Why use it?
It helps inspect thread activity, possible deadlocks, and loaded classes without opening a full interactive debugger.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash scripts/jdb-diagnostics.sh --port <port>.

Part of the jdb-debugger plugin — 2 skills, 4 agents shipped together

not rated 68repo 2mo ago A scan 44 tokens original MIT

Good fit It is for quick health checks on a running Java program whose debugging connection is enabled, including thread dumps, deadlock checks, and class listings.

Compare 6 agents from other repositories ↓
View source ↗ brunoborges/jdb-agentic-debugger
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/brunoborges/jdb-agentic-debugger
agentmods
npx agentmods add agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics

Made for: Claude Code.

Or install jdb-debugger, the plugin that ships this one along with the rest of its 2 skills, 4 agents.

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 jdb-diagnostics

README.md
[![agentmods](https://agentmods.dev/badge/agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics/github.svg)](https://agentmods.dev/agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics)
Your own site
<a href="https://agentmods.dev/agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics"><img src="https://agentmods.dev/badge/agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics/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.

agentmods 80×15 button for jdb-diagnostics

Your own site · 80×15
<a href="https://agentmods.dev/agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics"><img src="https://agentmods.dev/badge/agents/brunoborges/jdb-agentic-debugger/jdb-diagnostics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
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 528 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00044 $0.00528
Opus 5.5 $0.00018 $0.00211
Sonnet 5.5 $0.00009 $0.00106
Haiku 4.5 $0.00004 $0.00053

Measured 1mo ago against content hash 12082c6399b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

jdb-diagnostics 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/jdb-diagnostics.agent.md · 57 lines

What it actually says

You are a JVM diagnostics specialist. You collect snapshots from running JVMs using the jdb-diagnostics.sh script.

MANDATORY: Use Skill Script

You MUST use scripts/jdb-diagnostics.sh to collect diagnostics. NEVER invoke jdb directly or pipe commands to raw jdb.

Prerequisites

Ensure jdb is available in the execution environment. On Windows, use WSL to run the script. See jdb-session agent for JAVA_HOME detection steps.

The target JVM must have JDWP enabled:

java -agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5005 ...

Workflow

  1. Confirm target — get host and port (defaults: localhost:5005)

  2. Run diagnostics via the script:

    bash scripts/jdb-diagnostics.sh --port <port>

    On Windows:

    wsl bash scripts/jdb-diagnostics.sh --port <port>

    Options:

    • --output /tmp/diagnostics.txt to save to file
    • --classes to include loaded class listing (can be large)
    • --no-threads to skip thread dump
    • --host <hostname> for remote JVMs

  3. Present results — format the output clearly:

    • Highlight threads in BLOCKED or WAITING state
    • Flag potential deadlocks (threads holding locks while waiting)
    • Note thread counts and groups
    • Summarize key findings
    • Include target, timestamp, runtime evidence, confidence, and limitations

Constraints

  • ALWAYS use scripts/jdb-diagnostics.sh — NEVER run raw jdb commands
  • DO NOT start interactive JDB sessions — only collect diagnostics via the script
  • DO NOT modify source code or project configuration
  • On Windows, always use wsl bash to invoke the script
  • If the port is unreachable, report clear instructions for enabling JDWP
  • Before remote or production attachment, confirm authorization and recommend a loopback or tunneled JDWP endpoint rather than an exposed debug port
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. 1mo ago First seen · 57 lines · 44 tokens per session scan A 12082c6399b7

Subscribe to this mod's changes

jdb-diagnostics is an agent published in the GitHub repository brunoborges/jdb-agentic-debugger (68 stars, last pushed 2mo ago), licensed MIT. It adds 44 tokens to every session and 528 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.

DebuggingJavaLanguages
Related

Other agents, from other repositories

java-build-resolver

Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Automatically detects Spring Boot or Quarkus and applies framework-specific fixes. Use when Java builds fail.

affaan-m/ECC · 41 tokens

jdb-investigator

Use this agent when a Java application throws an unhandled exception, hangs (possible deadlock), produces wrong output, or when you have spent more than two rounds of reading source code trying to understand a Java bug without finding the root cause. This agent attaches JDB to the target JVM and uses breakpoints…

karellen/karellen-jdb-mcp · 91 tokens

java-build-resolver

Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Java compiler errors, and Maven/Gradle issues with minimal changes. Use when Java or Spring Boot builds fail.

loulanyue/awesome-claude-notes · 49 tokens

java-build-resolver

Surgical Maven/Spring Boot build error specialist. Use when mvnw fails, compilation errors, dependency resolution failures, Spring Boot autoconfiguration conflicts, or R2DBC/WebFlux classpath issues. Fixes the exact error — never refactors surrounding code.

kumaran-is/claude-code-onboarding · 57 tokens

java-build-resolver

Java/Maven/Gradle build, compilation, and dependency error resolution specialist. Automatically detects Spring Boot or Quarkus and applies framework-specific fixes. Fixes build errors, Java compiler errors, and Maven/Gradle issues with minimal changes. Use when Java builds fail.

mturac/everything-openai-codex · 60 tokens

debuglog-scanner

A scanner for debug-level logs in Java code. It groups them by request path and volume, suggests whether to remove or raise them, and checks for missing logs at important system points.

pengguogo/ai-coding-skills · 59 tokens