Claude Light — AI skill for Claude Code
claude_light.py is an interactive CLI chat tool for querying and editing a codebase using Claude.
How to install Claude Light
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open PIsberg/claude_light and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Claude Light does
claude_light.py is an interactive CLI chat tool for querying and editing a codebase using Claude. By combining Anthropic's prompt caching with a highly optimized hybrid RAG (Retrieval-Augmented Generation) pipeline, it drastically reduces API costs while maintaining full context of your project.
Alternatives in AI
- Startup Canvas — Generate Startup Canvas combining Product Strategy and Business Model 7.8k ★
- Ccstatusline — by sirmalloc - A highly customizable status line formatter for Claude Code CLI that displays model info, git b 5.5k ★
- Om Humanize — Voice-calibrated editing — makes Claude-drafted text sound like you wrote it, not like AI wrote it 4.6k ★
README
Claude Light: Auto-Warmer & Hybrid RAG Chat CLI
`claude_light.py` is an interactive CLI chat tool for querying and editing a codebase using Claude. By combining Anthropic's prompt caching with a highly optimized hybrid RAG (Retrieval-Augmented Generation) pipeline, it drastically reduces API costs while maintaining full context of your project.
**License:** Free for personal and hobby use ([PolyForm Noncommercial](LICENSE)). Commercial use requires a license — contact [Peter Isberg](mailto:isberg.peter+cl@gmail.com).

[](https://scorecard.dev/viewer/?uri=github.com/PIsberg/claude_light/)
📊 Real-World Benchmark Results
Measured against 4 popular Python open-source libraries, running the same 10 queries per repo with each tool (live API runs, 2026-03-23).
**Claude Code** = the Anthropic CLI (`claude --print`), each query in a fresh isolated session using its built-in tool-calling to fetch files on demand. **claude_light** = this project — hybrid RAG + prompt caching with automatic model routing.
Cost per 10 queries — Claude Code vs claude_light
| Repository | Repo size | Claude Code | claude_light | Savings |
|---|---|---|---|---|
psf/requests v2.31.0 |
108K tokens | $0.91 | $0.23 | 75% |
pallets/flask 3.0.0 |
144K tokens | $1.62 | $0.17 | 89% |
encode/httpx 0.25.2 |
191K tokens | $1.75 | $0.45 | 74% |
bottlepy/bottle 0.13.2 |
92K tokens | $1.52 | $0.30 | 80% |
| Total (≈40 queries) | $5.81 | $1.16 | 80% / 5× cheaper |
Why Claude Code costs more
Claude Code is a powerful general-purpose agentic tool and the cost difference reflects that:
- Its built-in system prompt and tool definitions consume ~35–40K tokens per session (cached, but cache-reads still cost $0.30/M).
- It always uses
Related Skills
CodeContext OS
Task-aware code intelligence for Claude Code and AI coding agents — combining AST structure, hybrid BM25 + FAI
Webinar Vibe Coding RAG
An attempt to live code a working Retrieval Augmented Generation app with AI coding tools
Ante
Ghost in your shell. Ante is a self-contained agent harness with a highly optimized core. It works like Claude
Vibeharness
Hackable, interactive LLM agent harness for the terminal — streaming REPL, tool-using agent loop, persistent P
Memory Lancedb Pro
Production-grade long-term memory system (v1.1.0-beta.8) for OpenClaw AI agents. Provides persistent, intellig
Mnem
Git for AI Agent Knowledge. A persistent, versioned memory layer for AI systems. Hybrid GraphRAG retrieval. Ru
Related Agents
Python RAG Backend Engineer
Production-grade Python RAG backend engineer specializing in ChromaDB vector storage, sentence-transformers em
Brain Analyst
The querying agent (agentic GraphRAG mode). Answers organizational questions using only the brain MCP tools, c
RAG Retriever
PROACTIVELY use this agent for dynamic external knowledge access during response generation. Specializes in do