What is NLWeb CLAUDE.md?

A project instruction file for Claude Code, describing NLWeb, a platform for adding conversational interfaces to websites, and the commands used to run and test it.

Use it when working on NLWeb code, especially to start its server, run tests, and follow the project's development rules.

It gives the coding agent repository-specific guidance and repeatable commands, reducing guesswork and preventing unrequested changes.

How nlweb-ai/NLWeb configures Claude Code

About the project

NLWeb is a Python reference implementation of protocols and tools for adding conversational natural-language interfaces to websites. It is intended for sites that want the same natural-language APIs to serve people and AI agents through MCP, using Schema.org and related web data formats. The catalogue instruction relates to working with this reference implementation.

nlweb-ai/NLWeb · 6,258 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to nlweb-ai/NLWeb. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/nlweb-ai/NLWeb/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/nlweb-ai/NLWeb

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/nlweb-ai/nlweb/claude-md/github.svg)](https://agentmods.dev/instructions/nlweb-ai/nlweb/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/nlweb-ai/nlweb/claude-md"><img src="https://agentmods.dev/badge/instructions/nlweb-ai/nlweb/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/nlweb-ai/nlweb/claude-md"><img src="https://agentmods.dev/badge/instructions/nlweb-ai/nlweb/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,149 This file is loaded in full into every session.

When invoked 1,149 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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 5.1	$0.01149	$0.01149
Opus 5.5	$0.00460	$0.00460
Sonnet 5.5	$0.00230	$0.00230
Haiku 4.5	$0.00115	$0.00115

Measured 2mo ago against content hash 0db16861ac34, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

NLWeb 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 2mo 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 · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 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.

MOST IMPORTANT GUIDELINE: Only implement exactly what you have been asked to. Do not add additional functionality. You tend to over complicate.

Project Overview

NLWeb is a conversational interface platform that enables natural language interactions with websites. It leverages Schema.org markup and supports MCP (Model Context Protocol) for AI agent interactions.

Common Development Commands

Running the Server

# Start aiohttp server (recommended)
./startup_aiohttp.sh

# Or directly from AskAgent/python
cd AskAgent/python
python -m webserver.aiohttp_server

Running Tests

# Quick test suite (from AskAgent directory)
cd AskAgent
./python/testing/run_all_tests.sh

# Comprehensive test runner with options
./python/testing/run_tests_comprehensive.sh -m end_to_end  # Specific test type
./python/testing/run_tests_comprehensive.sh --quick        # Quick smoke tests

# Run specific Python tests
cd AskAgent/python
python -m pytest testing/ -v

# Single test execution
python -m testing.run_tests --single --type end_to_end --query "test query"

Linting and Type Checking

# No standard lint/typecheck commands found in codebase
# Suggest adding these to the project if needed

Architecture Overview

Backend Architecture (AskAgent/python/)

Core Flow: Query → Pre-retrieval Analysis → Tool Selection → Retrieval → Ranking → Response Generation

Entry Point: webserver/aiohttp_server.py - Async HTTP server handling REST API and WebSocket connections
Request Processing Pipeline:
- core/baseHandler.py - Main request handler orchestrating the flow
- pre_retrieval/ - Query analysis, decontextualization, relevance detection
- methods/ - Tool implementations (search, item details, ensemble queries)
- retrieval/ - Vector database clients (Qdrant, Azure AI Search, Milvus, Snowflake, Elasticsearch)
- core/ranking.py - Result scoring and ranking
- llm/ - LLM provider integrations (OpenAI, Anthropic, Gemini, Azure, etc.)

Read the full file on GitHub · 136 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.

2mo ago First seen · 136 lines · 1,149 tokens per session scan A 0db16861ac34

Subscribe to this mod's changes

NLWeb CLAUDE.md is an instructions file published in the GitHub repository nlweb-ai/NLWeb (6,258 stars, last pushed 2mo ago), licensed MIT. It adds 1,149 tokens to every session, about $0.0046 per session on Opus 5.5. 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 2026-08-31.

NLWeb CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
NLWeb CLAUDE.mdnlweb-ai/NLWeb	Instructions file	6.3k	2mo ago	MIT	A	1,149	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

NLWeb: Instructions file for Claude Code