What is rag-cli CLAUDE.md?

Project instructions for Claude Code, an AI coding assistant, working on a local retrieval system that finds relevant document passages before generating answers.

Navigating the RAG-CLI codebase, understanding its document-search components, and following its package and documentation conventions.

They explain the repository structure and enforce rules such as avoiding emojis in project text.

rag-cli CLAUDE.md — Instructions file by ItMeDiaTech

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/itmediatech/rag-cli/claude-md

Clone the repo

git clone --depth 1 https://github.com/ItMeDiaTech/rag-cli

Per session 4,645 This file is loaded in full into every session.

When invoked 4,645 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	$0.04645	$0.04645
Opus 5	$0.02322	$0.02322
Sonnet 5	$0.00929	$0.00929
Haiku 4.5	$0.00464	$0.00464

Measured yesterday against content hash 4c1862a2eba7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rag-cli 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 yesterday.

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 · 596 lines

How it starts

The opening of the file, as written. The whole thing — 596 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.

CRITICAL: No Emojis Policy

NEVER use emojis in ANY documentation, plans, guides, or written output for this project UNLESS explicitly given permission. This includes:

README files
Documentation files
Code comments and docstrings
Plan descriptions
Commit messages
All text-based output

Focus on clear, professional documentation without decorative elements.

Project Overview

RAG-CLI v2.0 is a local Retrieval-Augmented Generation system designed as a Claude Code plugin. It processes documents locally, generates embeddings, stores vectors in ChromaDB, and uses claude-haiku-4-5-20251001 for response generation.

This version features a complete restructure with clean separation between core library and plugin code, marketplace-ready lifecycle management, and improved maintainability.

Project Structure (v2.0)

RAG-CLI/
 src/
    rag_cli/                          # CORE LIBRARY (plugin-agnostic)
       __init__.py                   # Version: 2.0.0
       core/                         # Core RAG functionality
          constants.py              # Centralized configuration
          document_processor.py     # Document chunking
          embeddings.py             # Embedding generation
          vector_store.py           # ChromaDB operations
          retrieval_pipeline.py     # Hybrid search + reranking
          claude_integration.py     # Claude API integration
          [30+ other core modules]
       agents/                       # Multi-agent framework
          base_agent.py             # Agent base class
          query_decomposer.py       # Query decomposition
          result_synthesizer.py     # Result synthesis
          maf/                      # Multi-Agent Framework
       integrations/                 # External integrations
          arxiv_connector.py        # ArXiv integration
          tavily_connector.py       # Tavily search
          maf_connector.py          # MAF integration
       cli/                          # Command-line tools
          index.py                  # rag-index command
          retrieve.py               # rag-retrieve command
       utils/                        # Shared utilities

    rag_cli_plugin/                   # PLUGIN CODE (Claude Code specific)
       __init__.py                   # Version: 2.0.0
       lifecycle/                    # Lifecycle management
          installer.py              # Marketplace installation
          updater.py                # Update handling
       commands/                     # Slash commands
          update_rag.py             # /update-rag command
          rag_project_indexer.py    # /rag-project command
          [other commands]
       hooks/                        # Event hooks
          user-prompt-submit.py     # Main RAG orchestration
          document-indexing.py      # Auto-indexing
          session-start.py          # Session initialization
          [other hooks]
       mcp/                          # MCP server
          unified_server.py         # Single unified MCP server
       services/                     # Plugin services
          service_manager.py        # Service registry
          dashboard.py              # Web dashboard
          tcp_server.py             # Monitoring server
          [monitoring modules]
       skills/                       # Agent skills

 config/                              # Configuration
    defaults/                        # Default configurations
       mcp.json                     # MCP server config
       rag_settings.json            # RAG settings
       services.json                # Service settings
       [other defaults]
    templates/                       # User-editable templates
       .env.template                # Environment template
       citation_config.json.template
    schemas/                         # JSON schemas
       settings.schema.json         # Settings validation

 scripts/                             # Scripts
    install/                         # Installation scripts
    update/                          # Update scripts
    utils/                           # Utility scripts
       update_imports_v2.py         # Import updater
       update_plugin_imports.py     # Plugin import updater

 .claude-plugin/                      # Plugin metadata
    plugin.json                     # Plugin configuration (v2.0.0)
    hooks.json                      # Hook configurations
    lifecycle.json                  # Lifecycle hooks (NEW)
    commands/                       # Command documentation

 data/                                # Runtime data
    vectors/                        # ChromaDB indexes
    cache/                          # Query cache
    documents/                      # Source documents

 logs/                                # Application logs
 tests/                               # Test suite
 docs/                                # Documentation

 pyproject.toml                       # Package configuration (v2.0.0)
 requirements.txt                     # Python dependencies
 README.md                            # Project README
 LICENSE                              # MIT License
 CHANGELOG.md                         # Version history

Read the full file on GitHub · 596 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.

yesterday First seen · 596 lines · 4,645 tokens per session scan A 4c1862a2eba7

Subscribe to this mod's changes

rag-cli CLAUDE.md is an instructions file published in the GitHub repository ItMeDiaTech/rag-cli (51 stars, last pushed 5mo ago), licensed MIT. It adds 4,645 tokens to every session, about $0.0232 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.

Data and AI Documents Multi-Agent RAG Writing and docs claude cli maf plugin

rag-cli CLAUDE.md

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

CRITICAL: No Emojis Policy

Project Overview

Project Structure (v2.0)

What this file has done since we first saw it

Other instructions, from other repositories

opencode-ensemble AGENTS.md

CoCoWork CLAUDE.md

corpus-ingest-core AGENTS.md

team-shinchan AGENTS.md

coordinate-agents AGENTS.md

fleet-memory CLAUDE.md