sparebank1-context

sparebank1-context is a skill for Claude Code, Codex from magnusrodseth/sparebank1-cli. It costs 138 tokens per session (1,791 once invoked), scanned A, original, MIT.

A private personal-finance context for the SpareBank 1 command-line tool, which displays bank accounts and transactions. It records information the bank cannot infer, such as what accounts and payments mean to you.

In plain words
What is it for?
Onboarding the user about their accounts and transactions, then saving the answers in a private file for future SpareBank 1 finance sessions.
Why use it?
Bank transaction data does not explain your personal goals or the meaning of each account. This context lets later finance sessions use that information without storing it in a shared project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Onboarding the user about their accounts and transactions, then saving the answers in a private file for future SpareBank 1 finance sessions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magnusrodseth/sparebank1-cli/sparebank1-context
Install

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.

Any agent
npx skills add magnusrodseth/sparebank1-cli --skill sparebank1-context
Clone the repo
git clone --depth 1 https://github.com/magnusrodseth/sparebank1-cli

Made for: Claude Code, Codex.

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 sparebank1-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/magnusrodseth/sparebank1-cli/sparebank1-context/github.svg)](https://agentmods.dev/skills/magnusrodseth/sparebank1-cli/sparebank1-context)
Your own site
<a href="https://agentmods.dev/skills/magnusrodseth/sparebank1-cli/sparebank1-context"><img src="https://agentmods.dev/badge/skills/magnusrodseth/sparebank1-cli/sparebank1-context/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.

agentmods 80×15 button for sparebank1-context

Your own site · 80×15
<a href="https://agentmods.dev/skills/magnusrodseth/sparebank1-cli/sparebank1-context"><img src="https://agentmods.dev/badge/skills/magnusrodseth/sparebank1-cli/sparebank1-context.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,791 The whole file, excluding the scripts and references it only reads on demand.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00138 $0.01791
Opus 5 $0.00069 $0.00896
Sonnet 5 $0.00028 $0.00358
Haiku 4.5 $0.00014 $0.00179

Measured 12d ago against content hash 6c5ceaefd08e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

sparebank1-context 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 12d 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.

skills/sparebank1-context/SKILL.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sparebank1-context

Turn sb1 from "shows transactions" into "reasons over your money". This skill runs a brief interview over the user's real data, then stores the answers as a personal finance context that future finance sessions load up front. Read sparebank1-shared first for auth and flags.

The CLI already surfaces the data. This skill captures the personal meaning layer the bank cannot infer, and nothing more.

The privacy contract (read this first)

This skill's mechanism is public (it ships in a public repo and installs for anyone), but the answers are private personal data. Therefore:

  • Write the context file to a user-owned path outside this repo. Default: ~/.config/sparebank1-cli/context.md (alongside where the file secret store writes). Override with the SB1_CONTEXT_FILE environment variable.
  • Never write answers, balances, account numbers, or counterparties into this repository, a commit, a PR, or any shared/cloud-synced location. Treat the file like the plaintext file secret store: keep it off backups and out of anything that syncs.
  • Prefer account names + last 4 digits over full account numbers. Don't record figures the user didn't ask you to keep.
  • The file is for this user's agent sessions. Don't paste its contents into chats, issues, or external services.

Resolve the path once at the start:

ctx="${SB1_CONTEXT_FILE:-$HOME/.config/sparebank1-cli/context.md}"
mkdir -p "$(dirname "$ctx")"

When to run

  • First time: no context file exists → run the full interview below.
  • Refresh: the file exists → read it, show the user what's captured, and only ask about what's new or changed (new counterparties, new Uncategorized rows, subscriptions to revisit). Don't re-ask settled questions.

Confirm login before pulling data:

sb1 status   # if not logged in, ask the user to run `sb1 login` (see sparebank1-shared)

Step 1 — gather the data (no code change needed)

Read the full file on GitHub · 163 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. 12d ago First seen · 163 lines · 138 tokens per session scan A 6c5ceaefd08e

Subscribe to this mod's changes

sparebank1-context is a skill published in the GitHub repository magnusrodseth/sparebank1-cli (22 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 1,791 once invoked, about $0.0007 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 2026-08-30.

Related

Other skills, from other repositories

tbank-transfer-money

A guide for sending money through T-Bank, including transfers by phone number, bank details, or payment QR code. T-Bank is a Russian bank, and SBP is Russia's instant interbank payment system.

icyberdeveloper/tbank-mcp · 135 tokens

tbank-bill-pay

A set of tools for paying bills through T-Bank, including utilities, phone service, internet, taxes, and traffic fines. It can inspect providers and payment fields before making a payment.

icyberdeveloper/tbank-mcp · 96 tokens

tbank-invest-advisor

An investment-analysis skill that uses T-Bank data to review brokerage accounts, holdings, transactions, profit and loss, returns, and allocation. A brokerage account is an account used to buy and sell investments such as shares, bonds, and exchange-traded funds.

icyberdeveloper/tbank-mcp · 98 tokens

tbank-messenger

A chat connection for T-Bank, a Russian bank, that lets an agent read conversations, download attachments, and contact bank support. It works with chats inside the bank app, not SMS codes or push notifications.

icyberdeveloper/tbank-mcp · 89 tokens

tbank-budget-analyzer

A financial analysis skill that uses T-Bank data to examine accounts, transactions, spending categories, subscriptions, recurring payments, and automatic payments. T-Bank is a Russian bank and financial services provider.

icyberdeveloper/tbank-mcp · 92 tokens

tbank-cards-documents

A read-only T-Bank connection for viewing card and account details, transactions, identity documents, insurance policies, and bank certificates.

icyberdeveloper/tbank-mcp · 112 tokens