What is gurbani-mcp CLAUDE.md?

Repository instructions for Gurbani MCP, a search and verification system for quotations from the Sri Guru Granth Sahib, the central scripture of Sikhism. It describes the project’s RAG search pipeline, MCP server, HTTP API, code stack, and source-data rules.

Use it when working on the repository’s Python code, SQLite search, optional semantic index, MCP tools, REST API, or Gurbani data handling.

It gives a coding agent the project context and emphasizes that Gurbani text must be reproduced exactly rather than paraphrased or altered.

How grusingh/gurbani-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to grusingh/gurbani-mcp. 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/grusingh/gurbani-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/grusingh/gurbani-mcp

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/grusingh/gurbani-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/grusingh/gurbani-mcp/claude-md)

Your own site

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

Per session 2,677 This file is loaded in full into every session.

When invoked 2,677 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	$0.02677	$0.02677
Opus 5.5	$0.01071	$0.01071
Sonnet 5.5	$0.00535	$0.00535
Haiku 4.5	$0.00268	$0.00268

Measured 2mo ago against content hash 52d2436d61a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gurbani-mcp 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 · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 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.

Project Purpose

A self-contained RAG pipeline, MCP server, and HTTP API for looking up and verifying Gurbani quotes against Sri Guru Granth Sahib (SGGS). This project covers SGGS only; other Banis present in the BaniDB seed are intentionally not extracted.

RAG pipeline — keyword search with Gurbani concept expansion over an SQLite database
MCP server — exposes Gurbani search/lookup/verify tools to MCP clients (Claude Desktop, Claude Code, Cursor)
HTTP API — the same tools over REST, for clients that can't speak MCP (e.g. a ChatGPT Custom GPT via Actions)

Authenticity is paramount — Gurbani text must be reproduced exactly as found in the source data, never paraphrased or altered.

Stack

Language: Python 3.11+
Package manager: uv (preferred)
Search: SQLite FTS via keyword matching + concept expansion (gurbani_rag/concepts.py)
Optional semantic search: ChromaDB + sentence-transformers (run scripts/build_index.py)
MCP: MCP Python SDK

Key Concepts

Shabad: A complete hymn/composition in the SGGS; the primary unit of search and retrieval
Ang: Page number in the SGGS (1–1430)
Gurbani: The sacred scripture text — must never be paraphrased, summarised, or altered

Data Sources

Gurbani data comes from the Khalis Foundation BaniDB — the dataset behind SikhiToTheMax. It ships as a seeded MariaDB inside the khalisfoundation/banidb-dev Docker image.

Nothing derived from BaniDB is committed to this repo — database/ is gitignored. Every user builds their own database/dist/banidb.sqlite locally via Docker (see below), since BaniDB's license doesn't cover redistributing the compiled dataset.

Unlike the source MariaDB, BaniDB carries a per-line English transliteration (Transliteration column) alongside the Gurmukhi and English translation — every SGGS line has all three.

Read the full file on GitHub · 197 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 · 197 lines · 2,677 tokens per session scan A 52d2436d61a4

Subscribe to this mod's changes

gurbani-mcp CLAUDE.md is an instructions file published in the GitHub repository grusingh/gurbani-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 2,677 tokens to every session, about $0.0107 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.

Learning and teaching Research

gurbani-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gurbani-mcp CLAUDE.mdgrusingh/gurbani-mcp	Instructions file	0	2mo ago	MIT	A	2,677	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

gurbani-mcp: Instructions file for Claude Code