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/grusingh/gurbani-mcp/claude-mdgit clone --depth 1 https://github.com/grusingh/gurbani-mcpWrote 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/grusingh/gurbani-mcp/claude-md)<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="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 5.1 | $0.02677 | $0.02677 |
| Opus 5 | $0.01339 | $0.01339 |
| Sonnet 5 | $0.00535 | $0.00535 |
| Haiku 4.5 | $0.00268 | $0.00268 |
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 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 — 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.
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 · 197 lines · 2,677 tokens per session scan A 52d2436d61a4
gurbani-mcp CLAUDE.md is an instructions file published in the GitHub repository grusingh/gurbani-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 2,677 tokens to every session, about $0.0134 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
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
AGENTS.md instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
agentic-ai-engineering-course AGENTS.md
AGENTS.md instructions for towardsai/agentic-ai-engineering-course, covering the what and course map (lessons ↔ code projects).
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.