local-ai-analyst CLAUDE.md

local-ai-analyst CLAUDE.md is an instructions file for coding agents from sbdk-dev/local-ai-analyst. It costs 2,076 tokens per session, scanned C, original, MIT.

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.

In plain words
What is it for?
It is for building or maintaining the local-ai-analyst project, including its architecture, analysis workflows, and MCP tools.
Why use it?
It helps keep analysis grounded in real query results and supports step-by-step exploration instead of made-up answers.

Instructions file

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/sbdk-dev/local-ai-analyst/claude-md
Clone the repo
git clone --depth 1 https://github.com/sbdk-dev/local-ai-analyst

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.

agentmods badge for local-ai-analyst CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sbdk-dev/local-ai-analyst/claude-md.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.svg" alt="Measured on agentmods" 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. 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.

ModelPer sessionOnce invoked
Fable 5 $0.02076 $0.02076
Opus 5 $0.01038 $0.01038
Sonnet 5 $0.00415 $0.00415
Haiku 4.5 $0.00208 $0.00208

Measured 4d ago against content hash 51bbc0e83861, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

  1. 4d 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 9mo ago), licensed MIT. It adds 2,076 tokens to every session, about $0.0104 per session on Opus 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.