Borrowing it
Nothing to install: this file belongs to magnusrodseth/sparebank1-cli. 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/magnusrodseth/sparebank1-cli/main/AGENTS.mdgit clone --depth 1 https://github.com/magnusrodseth/sparebank1-cliWrote 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/magnusrodseth/sparebank1-cli/agents-md)<a href="https://agentmods.dev/instructions/magnusrodseth/sparebank1-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/magnusrodseth/sparebank1-cli/agents-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/magnusrodseth/sparebank1-cli/agents-md"><img src="https://agentmods.dev/badge/instructions/magnusrodseth/sparebank1-cli/agents-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 | $0.01310 | $0.01310 |
| Opus 5.5 | $0.00524 | $0.00524 |
| Sonnet 5.5 | $0.00262 | $0.00262 |
| Haiku 4.5 | $0.00131 | $0.00131 |
Grade C, and why
sparebank1-cli AGENTS.md scanned grade C with 2 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 today.
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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/magnusrodseth/sparebank1-cli/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/magnusrodseth/sparebank1-cli/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents helping a user set up and use sb1, the SpareBank 1
personal banking CLI. If you are an agent and the user pointed you at this
repository, start here.
What this is
sb1 is a command-line tool for the
SpareBank 1 personal banking API. It lists
accounts, browses and exports transactions, and makes transfers, authenticated
with BankID over OAuth 2.0. Every command supports --json for machine-readable
output. It is personal and unofficial; usage is governed by the bank's terms
(see TERMS.md).
Install the binary
Prefer the prebuilt binary. It needs no Rust toolchain and does not call the GitHub API (so it is not affected by API rate limits):
curl -fsSL https://raw.githubusercontent.com/magnusrodseth/sparebank1-cli/main/install.sh | bash
- Installs to
~/.local/bin(override withSB1_INSTALL_DIR). - Pin a version with
SB1_VERSION=v1.1.0. - If the script reports that the install dir is not on
PATH, add it before continuing, then verify withsb1 --help. - macOS and Linux only. On other platforms, build from source:
cargo install --path ..
Set up access (the user must do this once)
sb1 talks to the bank on the user's behalf, so it needs their own API client
and a BankID login. You cannot do these steps for them:
- The user registers a personal client at
developer.sparebank1.no and notes the
client_idandclient_secret. - The redirect URI on that app must be exactly
http://localhost:12345/callback. - Provide the credentials via a git-ignored
.env(cp .env.example .env, then fill inCLIENT_ID/CLIENT_SECRET). - Run
sb1 login— this opens a browser for the interactive BankID flow. After login, the token is saved to the secret store and.envcan be deleted.
Secret storage backend is chosen with SB1_STORE (keychain default, op for
1Password, file for headless automation). See README.md → "Secret storage".
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.
- today Changed · +19 lines · +291 tokens per session 1455ace754e5
- 9d ago Changed · +15 lines · +200 tokens per session 95b2f9312a85
- 1mo ago First seen · 75 lines · 819 tokens per session scan C 5b7f67491351
sparebank1-cli AGENTS.md is an instructions file published in the GitHub repository magnusrodseth/sparebank1-cli (23 stars, last pushed yesterday), licensed MIT. It adds 1,310 tokens to every session, about $0.0052 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).