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 skills/fgforrest/mcp-jdwp-java/java-debugnpx skills add FgForrest/mcp-jdwp-java --skill java-debuggit clone --depth 1 https://github.com/FgForrest/mcp-jdwp-javaWhat 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 | $0.00060 | $0.08573 |
| Opus 5 | $0.00030 | $0.04287 |
| Sonnet 5 | $0.00012 | $0.01715 |
| Haiku 4.5 | $0.00006 | $0.00857 |
Grade A, and why
java-debug 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 yesterday.
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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Java Debug
Live debugging of a running JVM via JDWP. Replaces "add a println, re-run, repeat" with: set breakpoint -> hit it -> inspect everything -> mutate state -> resume.
Use when:
- A test fails and the assertion message doesn't tell you why
- An exception is buried under several layers of wrapping
- A value is wrong but you can't tell where it changes
- A bug only happens under specific conditions (race, off-by-one, edge case)
- Stepping through code in your head doesn't match what the runtime does
Don't use when:
- The bug is clear from code review alone
- You already know the fix and just need to write it
- It's a build/compile failure (not a runtime bug)
Prerequisites
The target JVM must be running with the JDWP agent. The port is whatever the developer (or their deployment) chose — port 5005 is only the convention for build-system test shortcuts. Long-running services very often expose JDWP on a different port (8003, 8000, 9009, …).
-agentlib:jdwp=transport=dt_socket,server=y,suspend=y,address=*:<port>
suspend=y blocks the JVM at startup until you attach — use for tests and early-startup bugs. suspend=n lets the JVM run freely — use for long-running services where you attach on demand.
Two attach scenarios:
- Launch-and-debug (tests, reproducers): start a fresh JVM yourself, usually via one of the quick-launch shortcuts below.
- Attach-to-running (services already up): skip the launch step entirely — go straight to attach. The port follows the resolution priority in the next section.
Quick launch shortcuts (these all default to port 5005):
- Maven Surefire:
mvn test -Dtest=<TestClass> -Dmaven.surefire.debug - Gradle:
./gradlew test --tests "com.example.MyTest" --debug-jvm - Standalone:
java -agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=*:5005 -jar app.jar
For build-system-specific gotchas (Surefire <argLine> overrides, Gradle maxParallelForks, bootRun) and the already-running-service workflow: see references/prerequisites.md.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 342 lines · 60 tokens per session scan A ca8b77aea530
java-debug is a skill published in the GitHub repository FgForrest/mcp-jdwp-java (24 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 8,573 once invoked, about $0.0003 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 skills, from other repositories
jdbg
Use when you need a Java program's real runtime state instead of reading source or adding print statements — the actual value of a variable/field/expression at a line, why an exception or NullPointerException is thrown (with stack + locals at the throw site), what a thread is blocked or deadlocked on, or how execution…
jdbg
Use the jdbg CLI to debug Java programs interactively from Pi when real runtime state is needed: variables, fields, expressions, exceptions, breakpoints, stepping, threads, locks, or JDWP attach. Pi should use the CLI because jdbg does not install an official Pi MCP server.
wxjava-api-contributor
按 WxJava 的 Maven 多模块、Java 8、公共 API 兼容性和 TestNG 约定，为微信官方接口新增或维护 SDK 支持。适用于新增 Service API、请求响应 Bean、序列化、HTTP 实现、Starter 配置或回归测试时。.
run-tests
Run project tests using Maven (mvn). Use when the user asks to run tests.
tika-eval-h2-query
Query the tika-eval H2 database directly for counts and joins the canned reports do not compute — connection gotchas, key tables, example queries. Use when the xlsx/summary.md reports are not enough.
search-m2
Search for Java classes inside Maven dependencies in /.m2. Use when the user asks to locate classes or inspect JARs. Cross-reference pom.xml files in the current directory to resolve dependency names/versions.