What is fusion CLAUDE.md?

A project instruction file for Fusion, a DuckDB-based analytics engine that reads data through a REST service and exposes it to AI tools. DuckDB is a database designed to run inside an application.

Working on Fusion code, including installation, tests, linting, demonstrations, MCP use, and REST-server operation.

It gives the coding agent the project's setup commands, architecture, data flow, and file layout in one place.

How yasinyaman/fusion configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to yasinyaman/fusion. 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/yasinyaman/fusion/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/yasinyaman/fusion

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/yasinyaman/fusion/claude-md/github.svg)](https://agentmods.dev/instructions/yasinyaman/fusion/claude-md)

Your own site

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

Per session 2,598 This file is loaded in full into every session.

When invoked 2,598 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	$0.02598	$0.02598
Opus 5.5	$0.01039	$0.01039
Sonnet 5.5	$0.00520	$0.00520
Haiku 4.5	$0.00260	$0.00260

Measured 1mo ago against content hash 41eaaeb5a2f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fusion 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 1mo 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 · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fusion OLAP Engine

DuckDB-powered in-memory analytics engine — LLM tool for data access via MCP, REST API, and the Python SDK. Hexagonal (ports & adapters) architecture since 1.0.0.

Project Overview

Language: Python 3.12+ (CI: 3.12 / 3.13 / 3.14)
Version: 1.1.0 (smart transfer: slices, streaming ingest, semi-joins, incremental refresh)
Core dependencies: DuckDB 1.5+, pyarrow, requests, sqlglot 30 (pandas is an optional extra)
Data source: Warp REST API (PostgreSQL/MySQL)
Tooling: uv (uv.lock is committed), ruff, mypy 2, pytest 9

Commands

Install: uv sync --all-extras
Test: uv run pytest (coverage gate fail_under = 80)
Lint: uv run ruff check fusion tests demo and uv run ruff format --check fusion tests demo
Types: uv run mypy fusion (strict flags on domain, ports, application)
Lock check: uv lock --check
Demo: uv run python -m demo.demo --scale 0.1
MCP server: uv run fusion-mcp --warp-url http://localhost:8000 --database mydb
REST server: uv run fusion-rest --warp-url http://localhost:8000 --auto-discover --port 9000

Always validate with uv run --frozen ...; the locked tool versions are newer than typical system installs.

Architecture

inbound adapters (REST, MCP, CLI, SDK)  ──►  application (FusionApp + services)  ──►  ports (Protocols)
                                                       │                                   ▲
                                                       ▼                                   │ implemented by
                                              domain (pure Python)             outbound adapters (DuckDB, sqlglot,
                                                                                memory cache, scheduler, Warp)
fusion.bootstrap.build_app(settings) wires adapters into the services.

Dependency rule (enforced by tests/architecture/test_dependency_rules.py, which walks every import including lazy ones):

Read the full file on GitHub · 132 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.

1mo ago Changed · +12 lines · +468 tokens per session 41eaaeb5a2f3
1mo ago Changed · +18 lines · +952 tokens per session 666def644098
2mo ago First seen · 102 lines · 1,178 tokens per session scan A 734484c3ea6e

Subscribe to this mod's changes

fusion CLAUDE.md is an instructions file published in the GitHub repository yasinyaman/fusion (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 2,598 tokens to every session, about $0.0104 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.

Analytics and metrics Databases

fusion CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
fusion CLAUDE.mdyasinyaman/fusion	Instructions file	2	1mo ago	Apache-2.0	A	2,598	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

fusion: Instructions file for Claude Code