advice

advice is a command for coding agents from peerjakobsen/smartspender. It costs 15 tokens per session (3,273 once invoked), scanned A, original, MIT.

A command for giving personal-finance advice from categorized spending and income records. It uses the Danish personal-finance framework, which is a set of principles for prioritizing household money decisions.

In plain words
What is it for?
Reviewing spending categories, subscriptions, monthly trends, past actions, and—if available—payslip income and pension data to suggest financial priorities.
Why use it?
It turns transaction history into practical priorities instead of requiring the user to interpret several CSV files themselves. Advice is more meaningful when at least a month of records is available.

Command

Part of the smartspender plugin — 13 skills, 19 commands shipped together

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.

agentmods
npx agentmods add commands/peerjakobsen/smartspender/advice
Clone the repo
git clone --depth 1 https://github.com/peerjakobsen/smartspender

Or install smartspender, the plugin that ships this one along with the rest of its 13 skills, 19 commands.

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 advice

README.md
[![agentmods](https://agentmods.dev/badge/commands/peerjakobsen/smartspender/advice.svg)](https://agentmods.dev/commands/peerjakobsen/smartspender/advice)
Your own site
<a href="https://agentmods.dev/commands/peerjakobsen/smartspender/advice"><img src="https://agentmods.dev/badge/commands/peerjakobsen/smartspender/advice.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00015 $0.03273
Opus 5 $0.00008 $0.01636
Sonnet 5 $0.00003 $0.00655
Haiku 4.5 $0.00002 $0.00327

Measured 4d ago against content hash fd1e13eabef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

advice 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 4d 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.

commands/advice.md · 297 lines

How it starts

The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/smartspender:advice

Trigger

  • /smartspender:advice
  • "Hvad bør jeg fokusere på?"
  • "Giv mig finansiel rådgivning"
  • "Hvor er jeg i min privatøkonomi?"
  • "What should I prioritize?"

Arguments

None.

Prerequisites

  • Transactions synced and analyzed (categorized.csv has data)
  • At least 1 month of transaction history for meaningful advice

Workflow

  1. Load user memory skill and read stored learnings:

    • Load skills/user-memory/SKILL.md for learning detection
    • Read learnings/preferences.md for previously stored user information
    • Note which questions can be skipped (emergency_fund, pension, debt, employer, etc.)
  2. Read data from CSV files:

    • categorized.csv: Spending by category
    • subscriptions.csv: Active subscriptions
    • monthly-summary.csv: Monthly totals and trends
    • action-log.csv: Previous actions taken
    • payslips.csv: Payslip data (if exists) for accurate income and pension info

1b. If payslips.csv exists and has data:

  • Load most recent payslip for the current/previous month
  • Extract: gross_salary, net_salary, pension_total, pension_pct
  • Set has_payslip_data = true
  • Use gross_salary for income-based calculations instead of transaction-derived income
  1. Calculate key metrics:

    • Monthly income:
      • If has_payslip_data: Use gross_salary from payslip
      • Otherwise: Sum of Indkomst category (net deposits)
    • Monthly expenses: Sum of all spending categories
    • Net cash flow: Income minus expenses
    • Savings rate:
      • If has_payslip_data: (gross_salary - expenses) / gross_salary (true savings rate)
      • Otherwise: Net cash flow / Income (approximate)
    • Subscription burden: Total subscriptions / Income (as percentage)
    • Essential vs discretionary split: (Bolig + Dagligvarer + Transport) vs rest
  2. Assess position in the 5-step framework using skills/danish-finance-guide/SKILL.md:

    Step 0: Budget — Always ✅ (user is tracking spending via SmartSpender)

Read the full file on GitHub · 297 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. 4d ago First seen · 297 lines · 15 tokens per session scan A fd1e13eabef3

Subscribe to this mod's changes

advice is a command published in the GitHub repository peerjakobsen/smartspender (5 stars, last pushed 7mo ago), licensed MIT. It adds 15 tokens to every session and 3,273 once invoked, about $0.0001 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.