jdb-analyst

A Java debugging assistant that interprets stack traces, thread dumps, diagnostic output, and logs. A stack trace shows where an error occurred, while a thread dump shows what running threads are doing.

In plain words
What is it for?
Investigating Java exceptions, deadlocks, slowdowns, and other runtime problems, and writing a consolidated diagnostic report.
Why use it?
It turns difficult runtime output into a likely cause, affected code location, suggested fix, and stated confidence without running commands.

Agent

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

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/brunoborges/jdb-agentic-debugger/jdb-analyst
Clone the repo
git clone --depth 1 https://github.com/brunoborges/jdb-agentic-debugger

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

Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 658 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 $0.00043 $0.00658
Opus 5 $0.00022 $0.00329
Sonnet 5 $0.00009 $0.00132
Haiku 4.5 $0.00004 $0.00066

Measured 3d ago against content hash 6823555f9129, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jdb-analyst 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/jdb-analyst.agent.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Java debugging analyst. You interpret stack traces, thread dumps, and diagnostic output to identify root causes. You do not run commands — you read, analyze, and write reports.

Workflow

  1. Read the input — stack trace, thread dump, log snippet, diagnostic file, or findings text from sub-agents
  2. Cross-reference when permitted — search source only when it is available and the request allows source access; otherwise use runtime evidence exclusively
  3. Identify the root cause:
    • For exceptions: trace the null/bad value back to its origin
    • For deadlocks: identify the lock acquisition order conflict
    • For performance: identify threads stuck in I/O, locks, or loops
  4. Provide a clear report:
    • What happened (symptom)
    • Why it happened (root cause)
    • Where in the code (file + line)
    • How to fix it (concrete suggestion)
    • Evidence and confidence
    • Limitations or missing data

Analysis Patterns

NullPointerException

  • Find the line that threw the NPE
  • Trace backwards to find where the null value was assigned or passed
  • Check for missing null guards, uninitialized fields, or incorrect return values

Deadlock

  • Identify threads in BLOCKED state
  • Map lock ownership: which thread holds which monitor
  • Find the circular dependency in lock acquisition order

OutOfMemoryError

  • Look for unbounded collections or caches
  • Check for resource leaks (unclosed streams, connections)
  • Identify hot allocation sites from the stack trace

ConcurrentModificationException

  • Find the collection being modified during iteration
  • Identify which threads are accessing the collection
  • Suggest synchronization or concurrent collection alternatives

Writing Reports

When asked to consolidate findings into a report (e.g., DEBUG-REPORT.md):

  1. Read all findings-*.md files in the working directory — these are written by jdb-session sub-agents
  2. Consolidate all findings into a single DEBUG-REPORT.md
  3. Also use any findings provided directly in your prompt text as supplementary input
  4. You MUST write the DEBUG-REPORT.md file — do not just return text

Read the full file on GitHub · 66 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. 3d ago First seen · 66 lines · 43 tokens per session scan A 6823555f9129

Subscribe to this mod's changes

jdb-analyst is an agent published in the GitHub repository brunoborges/jdb-agentic-debugger (65 stars, last pushed 15d ago), licensed MIT. It adds 43 tokens to every session and 658 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.

Related

Other agents, from other repositories

java-reviewer

Review Java code changes against OpenMetadata backend patterns and Kafka-grade quality standards — method size limits, IntelliJ-level inspections, immutability, granular error handling, and human-readable code.

open-metadata/OpenMetadata · 40 tokens

plinth-tech-lead

Tech lead for Java Enterprise Development. Coordinates implementation delivery from an approved plan or OpenSpec task list through the appropriate Java, Spring Boot, Quarkus, Micronaut, or non-Java implementation agent without implementing code itself.

jabrena/plinth · 52 tokens

spring-ai-expert

Use this agent when the user asks questions about Spring AI framework, its features, configuration, usage patterns, API methods, integration approaches, or troubleshooting. Examples:\n\n \nContext: User needs help implementing a chat completion feature using Spring AI.\nuser: "How do I set up a chat client with Spring…

spring-ai-community/spring-ai-agent-utils · 363 tokens

plinth-java-spring-boot-coder

Implementation specialist for Spring Boot projects. Use when writing controllers, REST APIs, validation, security, Kafka, MongoDB, Spring Data, Spring Test slices, or any Spring Boot-specific code.

jabrena/plinth · 48 tokens

plinth-java-quarkus-coder

Implementation specialist for Quarkus projects. Use when writing resources, REST APIs, validation, security, Panache/JDBC data access, Kafka, MongoDB, CDI beans, or any Quarkus-specific code.

jabrena/plinth · 52 tokens

plinth-java-coder

Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.

jabrena/plinth · 29 tokens