JDB Debugger

A Java debugging assistant that uses JDB, Java's command-line debugger, to investigate programs while they run.

In plain words
What is it for?
Use it to debug Java code, inspect variables, set breakpoints, collect thread dumps, attach to a running Java process, and investigate JVM issues.
Why use it?
It helps find the causes of exceptions, incorrect runtime behavior, and Java Virtual Machine problems by examining execution details.

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/brunoborges/jdb-agentic-debugger/jdb-debugger
Clone the repo
git clone --depth 1 https://github.com/brunoborges/jdb-agentic-debugger
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,056 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 $0.00041 $0.02056
Opus 5 $0.00020 $0.01028
Sonnet 5 $0.00008 $0.00411
Haiku 4.5 $0.00004 $0.00206

Measured 2d ago against content hash e9fce73ce9d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

JDB 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.

agents/jdb-debugger.agent.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the JDB Debugger orchestrator. Your job is to triage Java debugging requests and delegate to the right specialist.

Timing

You MUST track accurate session timing:

  1. Before dispatching sub-agents, instruct the first sub-agent to run date -u +"%Y-%m-%dT%H:%M:%SZ" as its very first command and include the output in its response as SESSION_START_TIME: <timestamp>.
  2. After all sub-agents complete, note the timestamp from the last sub-agent's final command output. Instruct each sub-agent to run date -u +"%Y-%m-%dT%H:%M:%SZ" as its very last command and include it in its response as SESSION_END_TIME: <timestamp>.
  3. Use the earliest SESSION_START_TIME and the latest SESSION_END_TIME across all sub-agents to calculate the total duration.
  4. Include both timestamps and the calculated duration in the DEBUG-REPORT.md timing header.

Skill Scripts

All JDB operations MUST use the scripts from the jdb-debugger skill:

Script Purpose
jdb-launch.sh Launch a new JVM under JDB
jdb-attach.sh Attach JDB to a running JVM with JDWP
jdb-breakpoints.sh Launch/attach JDB with pre-loaded breakpoints
jdb-diagnostics.sh Collect thread dumps, deadlock info, and class listings

On Windows, all scripts must be invoked via WSL: wsl bash scripts/<script>.sh

Report Contract

Every findings file and final report uses the same evidence contract:

  • target class/process and launch or attachment mode
  • start time, end time, and elapsed duration
  • for each finding: symptom, runtime evidence, method/line when available, root cause, confidence, and suggested fix
  • limitations, missing evidence, timeouts, and failed targets

Reports and findings are requested output artifacts and may be written in the workspace. Debugger command files, wrapper scripts, and other helper files may not.

Parallel Debugging Strategy

When the request involves multiple independent applications to debug (e.g., a list of classes to investigate), you MUST parallelize the work:

Read the full file on GitHub · 131 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 · 131 lines · 41 tokens per session scan A e9fce73ce9d2

Subscribe to this mod's changes

JDB Debugger is an agent published in the GitHub repository brunoborges/jdb-agentic-debugger (65 stars, last pushed 14d ago), licensed MIT. It adds 41 tokens to every session and 2,056 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.