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/releasenpx skills add FgForrest/mcp-jdwp-java --skill releasegit 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 | $0.00067 | $0.01977 |
| Opus 5 | $0.00034 | $0.00988 |
| Sonnet 5 | $0.00013 | $0.00395 |
| Haiku 4.5 | $0.00007 | $0.00198 |
Grade A, and why
release 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Release
End-to-end workflow for releasing the jdwp-debugging plugin from this repo.
Never push, force-push, tag-delete-on-remote, or merge without explicit user permission. Local commits and local tags are reversible; remote pushes are not.
What gets released (vs not)
| User-facing artifact | Bump on release? |
|---|---|
.claude-plugin/marketplace.json version |
YES — both occurrences |
CHANGELOG.md new section at top |
YES |
Annotated git tag vX.Y.Z |
YES |
pom.xml <version> (Maven artifact) |
NO — internal build id only |
jdwp-mcp-server/pom.xml <version> |
NO |
.mcp.json |
NO |
README.md |
NO (no version reference there) |
The plugin version (in marketplace.json) is decoupled from the Maven version. Don't try to keep them in sync.
Pre-flight checks
Run all of these before touching anything.
-
Identify the last release.
git for-each-ref --sort=-taggerdate --format='%(refname:short) %(taggerdate:short) %(subject)' refs/tags/ | head -5. The most recentvX.Y.Ztag is the baseline. Sanity-check: the latest[X.Y.Z]entry at the top ofCHANGELOG.mdmust equal theversionin.claude-plugin/marketplace.jsonand equal the most recent tag. If any of those three disagree, fix that drift before bumping. (We hit this in 2.2.0 —v2.1.2tag was missing and had to be back-filled.) -
Enumerate unreleased commits.
git log <last-tag>..HEAD --oneline --no-merges. Read the full bodies for anything ambiguous — the feature/fix/breaking signal lives in the commit body, not the subject. -
Pick the SemVer bump from the commit set:
- Any
feat:(new MCP tool, new behavior) → minor (X.Y+1.0). - Only
fix:/chore:/docs:/review:→ patch (X.Y.Z+1). - Any breaking change (removed/renamed MCP tool, changed default that breaks user scripts) → major (
X+1.0.0). - When in doubt between minor and patch, ask the user. The release plays out in public — over-bumping is fine, under-bumping is awkward.
- Any
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 · 150 lines · 67 tokens per session scan A c61eee9d2abf
release is a skill published in the GitHub repository FgForrest/mcp-jdwp-java (24 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,977 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.