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.
npx agentmods add instructions/yasinyaman/fusion/claude-mdgit clone --depth 1 https://github.com/yasinyaman/fusionWrote 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.
[](https://agentmods.dev/instructions/yasinyaman/fusion/claude-md)<a href="https://agentmods.dev/instructions/yasinyaman/fusion/claude-md"><img src="https://agentmods.dev/badge/instructions/yasinyaman/fusion/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01178 | $0.01178 |
| Opus 5 | $0.00589 | $0.00589 |
| Sonnet 5 | $0.00236 | $0.00236 |
| Haiku 4.5 | $0.00118 | $0.00118 |
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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 102 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 OpenAI Function Calling.
Project Overview
- Language: Python 3.10+
- Core dependency: DuckDB 1.2+
- Data source: Warp REST API (PostgreSQL/MySQL)
Commands
- Install:
pip install -e ".[all]" - Test:
pytest tests/ -v - Demo:
python -m demo.demo - Lint:
ruff check fusion/ - MCP Server:
fusion-mcp --warp-url http://localhost:8000 --database mydb - REST Server:
fusion-rest --warp-url http://localhost:8000 --auto-discover --port 9000
Architecture
Warp REST API --> WarpConnector --> DuckDB (in-memory)
(PostgreSQL/MySQL) |
LLM --> Tool Layer --> Result
(MCP / REST / SDK)
Three main layers:
- Data Source — Warp REST API connector (auto-discovery, pagination, schema inference, query pushdown)
- DuckDB Core — In-memory columnar store, materialized views, query cache, catalog manager, lazy loading
- LLM Tool Layer — 10 tools (MCP Server + REST API + OpenAI Function Calling), ToolExecutor, SQL guardrails
File Structure
fusion/
├── __init__.py # Public API exports
├── engine.py # OLAPEngine — main orchestration + pushdown routing
├── cache.py # QueryCache (LRU with TTL)
├── catalog.py # SchemaCatalog — multi-source metadata
├── guardrails.py # SQLGuardrails — blocks destructive SQL
├── result.py # QueryResult — output format conversions
├── strategy.py # FetchStrategy — smart table loading + pushdown eligibility
├── exceptions.py # Custom exception hierarchy
├── connectors/
│ ├── __init__.py # Connector registry (warp only)
│ ├── base.py # BaseConnector (abstract, supports_pushdown property)
│ └── warp.py # WarpConnector (Warp REST API client, pushdown capable)
├── tools/
│ ├── __init__.py # Tool layer exports
│ ├── definitions.py # 10 tool schemas (OpenAI + MCP format)
│ ├── executor.py # ToolExecutor — routes tool calls to engine
│ ├── mcp_server.py # MCP Server (stdio transport, FastMCP)
│ └── rest_server.py # REST API Server (FastAPI, Swagger UI)
└── views/
└── materialized.py # MaterializedViewManager
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.
- 5d ago First seen · 102 lines · 1,178 tokens per session scan A 734484c3ea6e
fusion CLAUDE.md is an instructions file published in the GitHub repository yasinyaman/fusion (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,178 tokens to every session, about $0.0059 per session on Opus 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.
Other instructions, from other repositories
lms-front CLAUDE.md
Claude Code instructions for guillermoscript/lms-front, covering claude.md, project overview, commands, architecture and multi-tenancy.
vespertide AGENTS.md
AGENTS.md instructions for dev-five-git/vespertide, covering vespertide knowledge base, structure, where to look, data flow and conventions.
seekstone CLAUDE.md
Claude Code instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
rails_ai_agents AGENTS.md
AGENTS.md instructions for ThibautBaissac/rails_ai_agents, covering project configuration, tech stack, architecture, key commands and tests.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
MCP-SqlServer CLAUDE.md
Claude Code instructions for Aron-Valenzuela/MCP-SqlServer, covering claude.md, project overview, setup (for each user), 1. install dependencies and 2. configure claude desktop.