agentmods.dev

jdb-agentic-debugger copilot-instructions.md

Project instructions for JDB Agentic Debugger, a plugin that teaches coding agents to debug Java programs with JDB, the command-line debugger included with the Java Development Kit. They describe the agents, scripts, documentation, and integration tests in the repository.

In plain words
What is it for?
Use them when changing or testing the debugger agents, interactive debugging sessions, Java virtual-machine diagnostics, stack-trace analysis, or the scripts and integration tests.
Why use it?
They give an agent the repository layout and rules needed to debug Java applications through the plugin without treating the repository as a normal Java application.

Instructions file for GitHub Copilot

65 14d ago A scan 714 tokens original MIT
View the source file brunoborges/jdb-agentic-debugger
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 instructions/brunoborges/jdb-agentic-debugger/copilot-instructions
Clone the repo
git clone --depth 1 https://github.com/brunoborges/jdb-agentic-debugger

Made for: GitHub Copilot.

Per session 714 This file is loaded in full into every session.
When invoked 714 The same file — it is already loaded in full.
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 $0.00714 $0.00714
Opus 5 $0.00357 $0.00357
Sonnet 5 $0.00143 $0.00143
Haiku 4.5 $0.00071 $0.00071

Measured 2d ago against content hash edd894b48b08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jdb-agentic-debugger copilot-instructions.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 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.

.github/copilot-instructions.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Copilot Instructions — JDB Agentic Debugger

What This Repository Is

This is an AI agent plugin (not a Java application). It teaches AI coding agents (GitHub Copilot CLI, Claude Code) to debug Java applications using JDB — the CLI debugger shipped with every JDK. The repo contains no application code; it consists entirely of agent definitions, skill documents, and Bash scripts.

Architecture

User → JDB Debugger (orchestrator agent)
         ├── jdb-session       → Interactive debugging (launch/attach, breakpoints, stepping)
         ├── jdb-diagnostics   → Quick JVM health checks (thread dumps, deadlock detection)
         └── jdb-analyst       → Read-only analysis (stack traces, root cause reports)
  • agents/ — Agent definition files (.agent.md) for the orchestrator and 3 sub-agents. Referenced by plugin.json.
  • skills/jdb-debugger/ — The JDB skill: SKILL.md (agent instructions), scripts/ (4 Bash scripts), references/ (JDB/JDWP docs).
  • .claude-plugin/plugin.json — Claude Code plugin manifest. Points to agents in agents/.
  • tests/ — Integration test framework that validates agents can autonomously debug intentionally buggy Java programs.

Key Conventions

  • Agents must never run raw jdb commands. All JDB operations go through the 4 scripts in skills/jdb-debugger/scripts/ (jdb-launch.sh, jdb-attach.sh, jdb-breakpoints.sh, jdb-diagnostics.sh).
  • Agents must never create helper or command files in the workspace. Requested output artifacts such as findings-*.md and DEBUG-REPORT.md are allowed. Use inline CLI flags (--bp, --cmd, --auto-inspect) for debugger input.
  • Agent files use YAML front matter with fields: name, description, tools, and optionally agents/handoffs.
  • The orchestrator (jdb-debugger.agent.md) never executes commands — it only triages and delegates via handoffs.

Running Tests

Tests are Bash-based integration tests that run AI agents against compiled Java programs with known bugs.

Read the full file on GitHub · 53 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 · 53 lines · 714 tokens per session scan A edd894b48b08

Subscribe to this mod's changes

jdb-agentic-debugger copilot-instructions.md is an instructions file published in the GitHub repository brunoborges/jdb-agentic-debugger (65 stars, last pushed 14d ago), licensed MIT. It adds 714 tokens to every session, about $0.0036 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.

DebuggingJavaLanguages
Related

Other instructions, from other repositories

WxJava AGENTS.md

AGENTS.md instructions for binarywang/WxJava, covering wxjava agent 指南, 适用范围与指令优先级, 项目概览, 开发流程 and 代码风格与兼容性.

binarywang/WxJava · 2,430 tokens

WxJava copilot-instructions.md

Copilot instructions for binarywang/WxJava, covering copilot instruction, wxjava - 微信 java sdk 开发说明, 高效开发指南, 前置条件与环境准备 and 引导、构建与校验.

binarywang/WxJava · 2,031 tokens

pulsar java-coding.instructions.md

Coding conventions for Apache Pulsar Java source and test code.

apache/pulsar · 86 tokens

azure-sdk-for-java AGENTS.md

AGENTS.md instructions for Azure/azure-sdk-for-java, covering agents.md, repository purpose, repository structure, agent capabilities and supported actions.

Azure/azure-sdk-for-java · 1,823 tokens

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）.

dromara/liteflow · 4,675 tokens

imgui-java AGENTS.md

Instructions for SpaiR/imgui-java, covering agents.md, what this repo is, project layout, build & test and upgrading dear imgui or an extension.

SpaiR/imgui-java · 3,576 tokens