What is local-ai-analyst CLAUDE.md?

Project instructions for an AI analyst that connects Claude Desktop and ChatGPT Desktop to data through MCP. It describes a semantic layer, which gives data consistent business meaning, and workflows for careful analysis.

It is for building or maintaining the local-ai-analyst project, including its architecture, analysis workflows, and MCP tools.

It helps keep analysis grounded in real query results and supports step-by-step exploration instead of made-up answers.

How sbdk-dev/local-ai-analyst configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to sbdk-dev/local-ai-analyst. 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/sbdk-dev/local-ai-analyst/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/sbdk-dev/local-ai-analyst

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/sbdk-dev/local-ai-analyst/claude-md/github.svg)](https://agentmods.dev/instructions/sbdk-dev/local-ai-analyst/claude-md)

Your own site

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

Per session 2,076 This file is loaded in full into every session.

When invoked 2,076 The same file — it is already loaded in full.

Security scan C 2 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	$0.02076	$0.02076
Opus 5.5	$0.00830	$0.00830
Sonnet 5.5	$0.00415	$0.00415
Haiku 4.5	$0.00208	$0.00208

Measured 2mo ago against content hash 51bbc0e83861, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

local-ai-analyst CLAUDE.md scanned grade C with 2 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

curl -LsSf https://astral.sh/uv/install.sh | sh

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -LsSf https://astral.sh/uv/install.sh | sh

CLAUDE.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Analyst System - Semantic Layer Integration

Project Overview

Goal: Build a semantic layer-powered AI analyst that connects to Claude Desktop and ChatGPT Desktop via MCP (Model Context Protocol), enabling natural language data analysis with statistical rigor and incremental exploration.

Status: v1.0 Production Ready | 100% Test Pass Rate | 23 MCP Tools

Architecture

┌─────────────────────────────────────────────────────────┐
│        Claude Desktop / ChatGPT Desktop                 │
└────────────────────┬────────────────────────────────────┘
                     │ MCP Protocol (23 Tools)
┌────────────────────▼────────────────────────────────────┐
│              FastMCP Server                             │
│  ┌─────────────────────────────────────────────────┐   │
│  │         Multi-Query Workflow Engine             │   │
│  │  • Dependency Resolution & Parallel Execution   │   │
│  │  • 3 Built-in Analytical Workflows              │   │
│  └─────────────────┬───────────────────────────────┘   │
│                    │                                    │
│  ┌─────────────────▼───────────────────────────────┐   │
│  │         Query Optimization Engine               │   │
│  │  • Intelligent Caching (95% hit rate)          │   │
│  │  • Performance Learning                        │   │
│  └─────────────────┬───────────────────────────────┘   │
│                    │                                    │
│  ┌─────────────────▼───────────────────────────────┐   │
│  │         Conversation Memory                     │   │
│  │  • 24-hour Context Window                      │   │
│  │  • Pattern Recognition                         │   │
│  └─────────────────┬───────────────────────────────┘   │
│                    │                                    │
│  ┌─────────────────▼───────────────────────────────┐   │
│  │         Intelligence Layer                      │   │
│  │  • Statistical Testing                         │   │
│  │  • Natural Language Generation                 │   │
│  └─────────────────┬───────────────────────────────┘   │
│                    │                                    │
│  ┌─────────────────▼───────────────────────────────┐   │
│  │         Semantic Layer (Ibis + DuckDB)         │   │
│  │  • Product Analytics Models                    │   │
│  │  • Business Logic & Metrics                    │   │
│  └─────────────────┬───────────────────────────────┘   │
└────────────────────┼────────────────────────────────────┘
                     │
               ┌─────▼──────┐
               │   DuckDB   │
               └────────────┘

Read the full file on GitHub · 293 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 · 293 lines · 2,076 tokens per session scan C 51bbc0e83861

Subscribe to this mod's changes

local-ai-analyst CLAUDE.md is an instructions file published in the GitHub repository sbdk-dev/local-ai-analyst (1 stars, last pushed 11mo ago), licensed MIT. It adds 2,076 tokens to every session, about $0.0083 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Data and AI ai dbt dlt duckdb ibis

local-ai-analyst CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
local-ai-analyst CLAUDE.mdsbdk-dev/local-ai-analyst	Instructions file	1	11mo ago	MIT	C	2,076	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	yesterday	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

local-ai-analyst: Instructions file for Claude Code