What is qqcode CLAUDE.md?

Project instructions for QQcode, an open-source command-line coding assistant that works with codebases through conversation, file tools, search, version control, and shell commands.

Use them when developing, testing, linting, formatting, or type-checking QQcode.

They tell a coding agent how to install dependencies, run QQcode, test it, check code quality, and understand its Python package layout.

qqcode CLAUDE.md — Instructions file by qnguyen3

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/qnguyen3/qqcode/claude-md

Clone the repo

git clone --depth 1 https://github.com/qnguyen3/qqcode

Per session 775 This file is loaded in full into every session.

When invoked 775 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.

Model	Per session	Once invoked
Fable 5	$0.00775	$0.00775
Opus 5	$0.00387	$0.00387
Sonnet 5	$0.00155	$0.00155
Haiku 4.5	$0.00077	$0.00077

Measured 2d ago against content hash 9b211ddd62d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

qqcode 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 · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 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.

Project Overview

QQcode is an open-source CLI coding assistant. It provides a conversational interface to codebases with tools for file manipulation, code searching, version control, and command execution.

Development Commands

# Install dependencies
uv sync --all-extras

# Run the CLI locally
uv run qqcode

# Run all tests (parallel by default)
uv run pytest

# Run a specific test file
uv run pytest tests/test_agent_tool_call.py

# Run tests with verbose output
uv run pytest -v

# Linting (check only)
uv run ruff check .

# Linting (auto-fix)
uv run ruff check --fix .

# Format code
uv run ruff format .

# Type checking
uv run pyright

# Run all pre-commit hooks
uv run pre-commit run --all-files

Architecture

Package Structure

vibe/cli/ - CLI entry point and Textual-based TUI
- entrypoint.py - Main entry point (qqcode command)
- textual_ui/ - Textual app, widgets, and event handlers
- autocompletion/ - Path and slash command autocompletion
vibe/core/ - Core agent logic
- agent.py - Main Agent class orchestrating LLM interactions and tool execution
- config.py - VibeConfig settings loaded from config.toml with Pydantic
- tools/ - Tool system (base classes, manager, built-in tools, MCP integration)
- llm/ - LLM backend abstraction (supports multiple providers)
- middleware.py - Request/response middleware (auto-compact, context warnings, limits)
- prompts/ - System prompt templates (markdown files)
vibe/acp/ - Agent Client Protocol server implementation
- Exposes QQcode as an ACP-compatible agent
vibe/setup/ - First-run onboarding flow

Key Components

Agent (vibe/core/agent.py): Central orchestrator that manages conversation flow, streams LLM responses, executes tools, and handles middleware pipeline.

Tool System (vibe/core/tools/):

BaseTool - Generic base class using Pydantic for args/result validation
ToolManager - Discovers and instantiates tools from built-in and custom directories
Built-in tools: bash, grep, read_file, write_file, edit, todo
MCP tools are dynamically created via proxy classes

Read the full file on GitHub · 89 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.

2d ago First seen · 89 lines · 775 tokens per session scan A 9b211ddd62d9

Subscribe to this mod's changes

qqcode CLAUDE.md is an instructions file published in the GitHub repository qnguyen3/qqcode (51 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 775 tokens to every session, about $0.0039 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.

Research Testing

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

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).

microsoft/vscode · 6,785 tokens

qqcode CLAUDE.md