Borrowing it
Nothing to install: this file belongs to PatilShreyas/debroid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/PatilShreyas/debroid/main/AGENTS.mdgit clone --depth 1 https://github.com/PatilShreyas/debroidWrote 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/patilshreyas/debroid/agents-md)<a href="https://agentmods.dev/instructions/patilshreyas/debroid/agents-md"><img src="https://agentmods.dev/badge/instructions/patilshreyas/debroid/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/patilshreyas/debroid/agents-md"><img src="https://agentmods.dev/badge/instructions/patilshreyas/debroid/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00606 | $0.00606 |
| Opus 5.5 | $0.00242 | $0.00242 |
| Sonnet 5.5 | $0.00121 | $0.00121 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
debroid AGENTS.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 1mo 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Contributor Guide 🤖
Welcome, fellow AI Agent! This document contains the context, motivation, and architectural guidelines you need to contribute to the Debroid repository effectively.
🎯 Intention & Motivation
The primary motivation behind Debroid is to bridge the gap between AI coding assistants and live Android environments. Traditional Android debugging relies heavily on the Android Studio GUI, making it nearly impossible for headless AI agents to set breakpoints, inspect runtime variables, or catch exceptions autonomously.
Debroid solves this by providing a lightweight, headless CLI wrapper around the Java Debug Wire Protocol (JDWP). It allows AI agents to orchestrate complex debugging sessions entirely through Standard I/O (terminal commands), empowering agents to solve deep runtime bugs in Android apps on behalf of users.
🏗️ Architecture & Layers
This project is structured into two main layers:
1. The core Layer (JDI & ADB Orchestration)
Path: core/src/main/kotlin/dev/shreyaspatil/debroid/
This is the heart of the debugger. It contains:
AdbManager: Automates shell interactions withadb(finding PIDs, forwarding JDWP ports, launching suspended apps).JdiSession&JdiSessionManager: Handles the actual Java Debug Interface (JDI) connection to the Android Virtual Machine. It manages breakpoints, memory inspections, stepping, and thread state via raw JDWP packets.
Note on core: This layer is completely isolated from the CLI and should only contain pure debugging and orchestration logic. All models returned here should be standard Kotlin data classes without serialization annotations.
2. The cli Layer (Daemon & Client)
Path: cli/src/main/kotlin/dev/shreyaspatil/debroid/cli/
This layer acts as the bridge between the AI Agent (the terminal) and the core layer.
- Daemon Server: Starts a persistent background socket server (
DaemonServer.kt). This is necessary because JDI connections must be held open continuously. - CLI Commands: Uses
Cliktto parse terminal commands (e.g.,debroid attach,debroid poll) and sends them as serialized IPC requests to the Daemon. - JSON Serialization: All outputs emitted by the CLI must be strict JSON (defined in
CliModels.kt). This ensures the AI Agent consuming the CLI output can parse the responses safely without regex.
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.
- 1mo ago First seen · 33 lines · 606 tokens per session scan A 92bc7bbc8c51
debroid AGENTS.md is an instructions file published in the GitHub repository PatilShreyas/debroid (276 stars, last pushed yesterday), licensed Apache-2.0. It adds 606 tokens to every session, about $0.0024 per session on Opus 5.5. 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.