openbanking-mcp: Instructions file for Claude Code

CLAUDE.md

openbanking-mcp CLAUDE.md is an instructions file for Claude Code from Beennnn/openbanking-mcp. It costs 2,641 tokens per session, scanned A, original, MIT.

A set of Claude Code instructions for the openbanking-mcp project. They describe a read-only banking tool, its Enable Banking data provider, configuration locations, and rules for handling the project.

In plain words
What is it for?
Use it when working on the openbanking-mcp repository so the assistant follows its naming, configuration, dependency, and banking-safety rules.
Why use it?
It gives the coding assistant project-specific boundaries before it changes or explains the code. The instructions state that the tool reads bank accounts and does not initiate payments.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md.

This is Beennnn/openbanking-mcp's own configuration. It tells Claude Code how to work on openbanking-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything openbanking-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Beennnn/openbanking-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/Beennnn/openbanking-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Beennnn/openbanking-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.

agentmods badge for openbanking-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/beennnn/openbanking-mcp/claude-md.svg)](https://agentmods.dev/instructions/beennnn/openbanking-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/beennnn/openbanking-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/beennnn/openbanking-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,641 This file is loaded in full into every session.
When invoked 2,641 The same file — it is already loaded in full.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02641 $0.02641
Opus 5 $0.01321 $0.01321
Sonnet 5 $0.00528 $0.00528
Haiku 4.5 $0.00264 $0.00264

Measured 6d ago against content hash 7212a7e585a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

openbanking-mcp CLAUDE.md scanned grade A with 1 finding 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 6d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Python 3.11+, **aucune dépendance tierce** — `urllib` pour l'HTTP, JSON-RPC écrit à la
CLAUDE.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

openbanking-mcp — lecture seule des comptes, et le brief qui prévient avant

Le dépôt s'appelle openbanking-mcp, la commande s'appelle bankread, et les chemins de configuration suivent la commande (~/.config/bankread, trousseau bankread-enablebanking). Le nom du dépôt dit ce que c'est — c'est comme ça qu'on le trouve — le nom de la commande dit ce qu'on en fait. Ne pas « harmoniser » : renommer la commande toucherait le dossier de configuration, le trousseau, l'agent launchd et toute déclaration MCP existante, pour rien.

Outil personnel, publié tel quel (MIT, dépôt public). Deux choses, et rien d'autre : lire ses comptes bancaires par la DSP2 (agrément AIS, jamais d'initiation de paiement), et en tirer un brief quotidien qui pose quelques tâches Todoist.

Python 3.11+, aucune dépendance tierceurllib pour l'HTTP, JSON-RPC écrit à la main pour MCP. Ne pas en ajouter : rien ici ne le justifie, et une dépendance de plus, c'est une mise à jour de plus à surveiller sur un outil qui touche à de l'argent.

Le fournisseur de données : Enable Banking

bankreadlib/gocardless.py visait GoCardless Bank Account Data (ex-Nordigen), fermé aux nouvelles inscriptions et en cours d'arrêt (vérifié le 2026-08-20). Il est gardé pour un compte déjà ouvert, il ne sert à personne d'autre.

Le fournisseur courant est Enable Banking, palier Restricted Production : vraie donnée de production, restreinte aux comptes qu'on déclare soi-même dans leur portail, gratuit, inscription en libre-service par email — ni société ni certificat eIDAS. Le tour des alternatives et les sources sont dans docs/fournisseurs.md : s'y référer plutôt que d'écrire de mémoire, et le mettre à jour si le paysage bouge.

bankreadlib/rs256.py signe les jetons sans dépendance : RS256 se ramène à hashlib plus pow(m, d, n). Le test test_la_signature_est_celle_d_openssl compare octet pour octet à openssl dgst -sha256 -sign — c'est ce qui autorise à se passer de PyJWT et de cryptography. Ce module ne doit jamais servir à VÉRIFIER une signature venue de l'extérieur : une implémentation maison n'a aucune protection contre la mesure du temps de calcul.

Read the full file on GitHub · 168 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.

  1. 6d ago First seen · 168 lines · 2,641 tokens per session scan A 7212a7e585a5

Subscribe to this mod's changes

openbanking-mcp CLAUDE.md is an instructions file published in the GitHub repository Beennnn/openbanking-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 2,641 tokens to every session, about $0.0132 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other instructions, from other repositories

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

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.

vercel/next.js · 7,296 tokens

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.

langchain-ai/langchain · 4,469 tokens

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).

microsoft/vscode · 5,001 tokens

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.

github/spec-kit · 7,104 tokens