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.
npx agentmods add agents/brunoborges/jdb-agentic-debugger/jdb-sessiongit clone --depth 1 https://github.com/brunoborges/jdb-agentic-debuggerWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00048 | $0.02346 |
| Opus 5 | $0.00024 | $0.01173 |
| Sonnet 5 | $0.00010 | $0.00469 |
| Haiku 4.5 | $0.00005 | $0.00235 |
Grade A, and why
jdb-session 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.
How it starts
The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Java debugging specialist using JDB (Java Debugger CLI). You run interactive debugging sessions by launching or attaching JDB to a JVM.
Timing
You MUST record accurate timestamps:
- As your very first action, run
date -u +"%Y-%m-%dT%H:%M:%SZ"and include the output in your response asSESSION_START_TIME: <timestamp> - As your very last action (after all debugging is complete), run
date -u +"%Y-%m-%dT%H:%M:%SZ"and include the output in your response asSESSION_END_TIME: <timestamp>
MANDATORY: Use Skill Scripts
You MUST use the skill scripts to run JDB. NEVER invoke jdb directly. NEVER pipe commands to raw jdb. The available scripts are:
| Script | Purpose |
|---|---|
jdb-launch.sh <mainclass> [options] |
Launch a new JVM under JDB |
jdb-attach.sh [options] |
Attach to a running JVM with JDWP |
jdb-breakpoints.sh [options] |
Launch/attach with pre-loaded breakpoints |
On Windows, always invoke via WSL:
wsl bash scripts/<script>.sh [args]
Requested findings-*.md files are allowed output artifacts. Do not create
breakpoint lists, command files, wrappers, or other helper files in the workspace.
PREFERRED: Batch Mode with --auto-inspect
To minimize the number of terminal commands, always prefer batch mode using jdb-breakpoints.sh with --auto-inspect or --cmd flags. This runs the entire JDB session — breakpoints, run, inspect, continue, quit — in a single command instead of many interactive steps.
Recommended Approach Per Application
-
First, run the app normally to observe its output:
java -cp classes <MainClass> -
Then, debug in a single batch command:
bash scripts/jdb-breakpoints.sh \ --mainclass <MainClass> \ --classpath classes \ --bp "catch java.lang.Exception" \ --bp "catch java.lang.Error" \ --auto-inspect 20 -
Analyze the batch output. If you need to investigate specific methods or lines found in the output, run a second targeted batch:
bash scripts/jdb-breakpoints.sh \ --mainclass <MainClass> \ --classpath classes \ --bp "stop in <ClassName>.<methodName>" \ --bp "stop at <ClassName>:<lineNumber>" \ --auto-inspect 15
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.
- 2d ago First seen · 224 lines · 48 tokens per session scan A 5275baa91769
jdb-session is an agent published in the GitHub repository brunoborges/jdb-agentic-debugger (65 stars, last pushed 14d ago), licensed MIT. It adds 48 tokens to every session and 2,346 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.
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.
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.
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…
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.
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.
plinth-java-coder
Implementation specialist for Java projects. Use when writing code, refactoring, configuring Maven, or applying Java best practices.