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/hzhaoy/deep-code-agent/agents-mdgit clone --depth 1 https://github.com/hzhaoy/deep-code-agentWhat 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 | $0.01478 | $0.01478 |
| Opus 5 | $0.00739 | $0.00739 |
| Sonnet 5 | $0.00296 | $0.00296 |
| Haiku 4.5 | $0.00148 | $0.00148 |
Grade A, and why
deep-code-agent 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 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Deep Code Agent
Project Overview
Deep Code Agent is an AI-powered coding assistant built on the DeepAgents framework. It provides a multi-agent system with specialized subagents for various software development tasks.
Architecture
src/deep_code_agent/
├── __init__.py # Package exports and entry point
├── __main__.py # Module execution entry point
├── cli.py # Command-line interface implementation
├── config.py # Configuration constants and defaults
├── prompts.py # System prompts and subagent configurations
├── code_agent.py # Main agent creation and orchestration
├── models/
│ └── llms/
│ └── langchain_chat.py # LLM integration layer
├── tools/
│ ├── __init__.py
│ └── terminal.py # Terminal command execution tool
└── tui/ # Terminal User Interface
├── __init__.py
├── app.py # Main TUI application
├── bridge/ # Agent-bridge layer
│ ├── __init__.py
│ ├── agent_bridge.py
│ └── stream_handler.py
├── screens/ # TUI screens
│ ├── __init__.py
│ ├── main_screen.py
│ └── approval_modal.py
├── widgets/ # Reusable widgets
│ ├── __init__.py
│ ├── chat_log.py
│ ├── input_box.py
│ ├── message_bubble.py
│ ├── side_panel.py
│ ├── status_bar.py
│ └── tool_call_view.py
├── styles/ # TUI styles
│ ├── __init__.py
│ └── main.tcss
└── utils/
└── __init__.py
Key Components
1. Config (config.py)
Centralized configuration for:
- Timeout settings (
MAX_TIMEOUT=300,DEFAULT_TIMEOUT=30) - Human-in-the-loop defaults (
DEFAULT_INTERRUPT_ON)
2. Prompts (prompts.py)
Defines system prompt templates and subagent configurations:
get_system_prompt(): Main agent system promptcreate_subagent_configurations(): Creates 5 specialized subagents:code_reviewer: Code review and quality analysistest_writer: Test generation and TDDdocumenter: Documentation creationdebugger: Debugging and error resolutionrefactorer: Code refactoring and optimization
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 · 210 lines · 1,478 tokens per session scan A 7b31e5c6b596
deep-code-agent AGENTS.md is an instructions file published in the GitHub repository hzhaoy/deep-code-agent (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,478 tokens to every session, about $0.0074 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 instructions, from other repositories
qwen-code CLAUDE.md
Instructions for QwenLM/qwen-code: This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
teaql-agent-kit AGENTS.md
Instructions for teaql/teaql-agent-kit, covering agents.md — teaql agent kit and hard requirements.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
loongsuite-pilot AGENTS.md
Instructions for alibaba/loongsuite-pilot, covering loongsuite-pilot 项目导航, 架构总览, 模块清单, agent 采集矩阵 and 依赖关系.
loongsuite-pilot CLAUDE.md
Instructions for alibaba/loongsuite-pilot: See AGENTS.md for project architecture, module docs, and development guidelines.
roamcode AGENTS.md
Instructions for burakgon/roamcode, covering repository instructions for coding agents, public-repository safety, stable release and ota contract, releasing a stable version and ota changes.