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 instructions/dronsv/jdwp-mcp/claude-mdgit clone --depth 1 https://github.com/dronsv/jdwp-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/dronsv/jdwp-mcp/claude-md)<a href="https://agentmods.dev/instructions/dronsv/jdwp-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/dronsv/jdwp-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01016 | $0.01016 |
| Opus 5 | $0.00508 | $0.00508 |
| Sonnet 5 | $0.00203 | $0.00203 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
jdwp-mcp CLAUDE.md 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 4d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Is
jdwp-mcp is an MCP (Model Context Protocol) server that enables LLMs to debug Java applications via JDWP (Java Debug Wire Protocol). It's a Rust workspace with two crates:
- jdwp-client: Low-level JDWP protocol client library (TCP connection, binary packet encoding/decoding, event loop)
- mcp-server: MCP server binary (
jdwp-mcp) that translates MCP JSON-RPC over stdio into JDWP commands
Build Commands
cargo build # debug build
cargo build --release # release build (binary at target/release/jdwp-mcp)
cargo test # run all tests
cargo test -p jdwp-client # test just the client crate
cargo test -p jdwp-mcp # test just the MCP server crate
Architecture
LLM (Claude Code) --[stdio JSON-RPC]--> mcp-server --[JDWP binary over TCP]--> JVM
jdwp-client crate
The client implements JDWP over an async event loop:
connection.rs—JdwpConnection: TCP connect, JDWP handshake, entry point for sending commandseventloop.rs—EventLoopHandle: tokio task that multiplexes outgoing commands and incoming replies/events on one TCP stream. Commands get routed by packet ID; events go to an mpsc channel. Commands can be sent from multiple tasks; events should be consumed by one.protocol.rs—CommandPacket/ReplyPacket: binary encoding/decoding (big-endian, architecture-independent)commands.rs— JDWP command set/command constants (mirrors the spec)types.rs—Value,Location,Variable, type tagsevents.rs— Event parsing (breakpoint, step, thread start/death, VM death)vm.rs,thread.rs,method.rs,reftype.rs,stackframe.rs,object.rs,string.rs— Higher-level command wrappers organized by JDWP command setreader.rs— Cursor-based reader for JDWP data with variable-width ID fieldseventrequest.rs— Event request building (breakpoints, stepping)
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.
- 4d ago First seen · 93 lines · 1,016 tokens per session scan A 7efb63ecc472
jdwp-mcp CLAUDE.md is an instructions file published in the GitHub repository dronsv/jdwp-mcp (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,016 tokens to every session, about $0.0051 per session on Opus 5. A static security scan graded it A with 0 findings. It comes from a forked repository.
Other instructions, from other repositories
quarkus-workshop-langchain4j AGENTS.md
AGENTS.md instructions for quarkusio/quarkus-workshop-langchain4j, covering agents.md, project overview, technology stack, project structure and building and running.
agentscope-java code-review.instructions.md
Instructions for agentscope-ai/agentscope-java, covering java code standards, security check, performance check, documentation sync check and pr title check.
LSP4J-MCP AGENTS.md
AGENTS.md instructions for stephanj/LSP4J-MCP, covering agents.md, project overview, build and run commands, build shaded jar and run tests.
questdb CLAUDE.md
Claude Code instructions for questdb/questdb, covering claude.md, project overview, coding guidelines, tests and questdb's sql dialect.
liteflow CLAUDE.md
Instructions for dromara/liteflow, covering claude.md, 概述, 命令, 构建 and 构建整个项目(模块集由 jdk 版本自动选择 —— 见下方说明).
BitcoinAddressFinder CLAUDE.md
Claude Code instructions for bernardladenthin/BitcoinAddressFinder, covering claude.md — bitcoinaddressfinder, project overview, build system, common commands and compile only.