deep-code-agent CLAUDE.md

Development instructions for Deep Code Agent, a Python command-line coding agent with an optional terminal user interface. They describe its commands, package layout, dependencies, and tests.

In plain words
What is it for?
Use them when developing or maintaining Deep Code Agent, including its command-line interface, terminal screens, model integrations, agent tools, and tests.
Why use it?
They give an AI coding agent the project conventions and exact commands needed to install, run, test, build, or edit the tool safely.

Instructions file

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/hzhaoy/deep-code-agent/claude-md
Clone the repo
git clone --depth 1 https://github.com/hzhaoy/deep-code-agent
Per session 1,271 This file is loaded in full into every session.
When invoked 1,271 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 $0.01271 $0.01271
Opus 5 $0.00635 $0.00635
Sonnet 5 $0.00254 $0.00254
Haiku 4.5 $0.00127 $0.00127

Measured 2d ago against content hash 6e9e946e621f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deep-code-agent 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 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.

CLAUDE.md · 228 lines

How it starts

The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Deep Code Agent

Quick Reference

  • Package Name: deep_code_agent
  • Entry Point: uv run deep-code-agent
  • Python Version: 3.10+
  • Package Manager: uv

Common Commands

# Install dependencies
uv sync

# Run the CLI
uv run deep-code-agent

# Run with specific options
uv run deep-code-agent --backend-type filesystem --model-name gpt-4

# Run with TUI mode
uv run deep-code-agent --tui

# Run tests
uv run pytest tests/

# Build package
uv build

# Install in editable mode
uv pip install -e .

Project Structure

src/deep_code_agent/
├── __init__.py          # Package exports
├── __main__.py          # Module entry point
├── cli.py               # CLI implementation
├── config.py            # Configuration constants
├── prompts.py           # System prompts and subagents
├── code_agent.py        # Main agent creation
├── models/llms/         # LLM integrations
├── tools/               # Agent tools
└── tui/                 # Terminal User Interface
    ├── app.py            # Main TUI application
    ├── bridge/            # Agent-bridge layer
    │   ├── agent_bridge.py
    │   └── stream_handler.py
    ├── screens/           # TUI screens
    │   ├── main_screen.py
    │   └── approval_modal.py
    ├── widgets/           # Reusable widgets
    │   ├── chat_log.py
    │   ├── input_box.py
    │   ├── message_bubble.py
    │   ├── side_panel.py
    │   ├── status_bar.py
    │   └── tool_call_view.py
    └── styles/            # TUI styles
        └── main.tcss

Key Patterns

1. Creating a Code Agent

from deep_code_agent import create_code_agent

# State backend (default)
agent = create_code_agent(
    codebase_dir="/path/to/code",
    backend_type="state"
)

# Filesystem backend (with terminal tool)
agent = create_code_agent(
    codebase_dir="/path/to/code",
    backend_type="filesystem"
)

2. Configuration Constants

All configuration is centralized in config.py:

from deep_code_agent.config import (
    MAX_TIMEOUT,          # 300 seconds
    DEFAULT_TIMEOUT,      # 30 seconds
    DEFAULT_INTERRUPT_ON # HITL defaults
)

Read the full file on GitHub · 228 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 · 228 lines · 1,271 tokens per session scan A 6e9e946e621f

Subscribe to this mod's changes

deep-code-agent CLAUDE.md is an instructions file published in the GitHub repository hzhaoy/deep-code-agent (11 stars, last pushed 1mo ago), licensed MIT. It adds 1,271 tokens to every session, about $0.0064 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.