Borrowing it
Nothing to install: this file belongs to angelina10504/bharatpay-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.
curl -O https://raw.githubusercontent.com/angelina10504/bharatpay-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/angelina10504/bharatpay-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/angelina10504/bharatpay-mcp/claude-md)<a href="https://agentmods.dev/instructions/angelina10504/bharatpay-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/angelina10504/bharatpay-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.
<a href="https://agentmods.dev/instructions/angelina10504/bharatpay-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/angelina10504/bharatpay-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01969 | $0.01969 |
| Opus 5 | $0.00984 | $0.00984 |
| Sonnet 5 | $0.00394 | $0.00394 |
| Haiku 4.5 | $0.00197 | $0.00197 |
Grade A, and why
bharatpay-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 11d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude Code working in this repo.
What this is
bharatpay-mcp — a public MCP server (PyPI: bharatpay-mcp, MIT) that exposes Indian
fintech utilities to AI agents over stdio: IFSC lookups, PAN/GSTIN validation, pincode
lookups, mutual fund NAVs, UPI VPA identification, INR formatting. Seven tools, no auth,
no API keys, no paid upstreams.
It deliberately complements Razorpay's official MCP server rather than competing: Razorpay executes transactions, BharatPay validates and enriches. Keep that boundary — don't add tools that move money or need credentials.
Layout
src/bharatpay_mcp/
server.py # FastMCP instance + all @mcp.tool() registrations. Thin wrappers only.
__main__.py # `python -m bharatpay_mcp` → server.main()
tools/ # one module per domain; all real logic lives here
gstin.py ifsc.py inr.py mutual_fund.py pan.py pincode.py upi.py
tests/test_validators.py # offline validators only, no network
scripts/smoke_test.py # manual end-to-end incl. live APIs (not part of pytest)
Engineering standards
These are the rules that matter here. Follow them; don't relax them for convenience.
1. Every tool has a pure-function offline validator
Each tool module must be able to reject bad input without touching the network. Format checks, checksums, and metadata extraction are pure functions over strings — they run before any HTTP call and they never raise.
- Fully offline tools (
pan.py,gstin.py,upi.py,inr.py) are pure end to end. - Network tools validate first, then fetch: see
_validate_format()in ifsc.py andPIN_PATTERNin pincode.py.
The point is graceful degradation: when ifsc.razorpay.com or India Post is down, a
malformed IFSC still gets a precise, useful answer, and a well-formed one gets an
honest network error — never a traceback across the MCP boundary.
Known gap: mutual_fund.py only checks for an empty query before hitting AMFI. If you touch that file, add a real offline validator (scheme codes are digits; name fragments have a minimum length) and a test.
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.
- 11d ago First seen · 179 lines · 1,969 tokens per session scan A 90ae8dcc595d
bharatpay-mcp CLAUDE.md is an instructions file published in the GitHub repository angelina10504/bharatpay-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,969 tokens to every session, about $0.0098 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).