next-dollar

next-dollar is a skill for Claude Code from weklund/fiduciary. It costs 112 tokens per session (2,352 once invoked), scanned A, original, MIT.

A procedure for deciding where a person's next dollar should go based on their actual finances, debts, rates, goals, and constraints.

In plain words
What is it for?
Use it when allocating a paycheck, bonus, raise, tax refund, savings, or other money between expenses, debt payments, saving, and investing.
Why use it?
It replaces generic money advice with a specific order of priorities for the person's situation.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument.

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 skills/weklund/fiduciary/next-dollar
Any agent
npx skills add weklund/fiduciary --skill next-dollar
Clone the repo
git clone --depth 1 https://github.com/weklund/fiduciary

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 next-dollar

README.md
[![agentmods](https://agentmods.dev/badge/skills/weklund/fiduciary/next-dollar.svg)](https://agentmods.dev/skills/weklund/fiduciary/next-dollar)
Your own site
<a href="https://agentmods.dev/skills/weklund/fiduciary/next-dollar"><img src="https://agentmods.dev/badge/skills/weklund/fiduciary/next-dollar.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,352 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 5.1 $0.00112 $0.02352
Opus 5 $0.00056 $0.01176
Sonnet 5 $0.00022 $0.00470
Haiku 4.5 $0.00011 $0.00235

Measured 6d ago against content hash 18ab5c17ea07, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

next-dollar 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 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.

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.

.claude/skills/next-dollar/SKILL.md · 267 lines

How it starts

The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Next Dollar Guidance

You are answering the most fundamental personal finance question: "What should I do with my next dollar?" This isn't generic advice — you're applying the financial order of operations to THIS PERSON's specific balances, rates, goals, and constraints.

Process

  1. Determine how much they're allocating (ask if not stated)
  2. Gather their current financial state
  3. Walk the order of operations, checking each step against reality
  4. Identify where THEY are in the sequence
  5. Give a specific, actionable recommendation with the math

Step 1: Clarify the Amount

If the user didn't specify an amount, ask: "How much are we working with — a specific amount like a bonus, or thinking about your ongoing monthly allocation?"

Common triggers and what they mean:

  • "I have $X" → one-time allocation
  • "Got a raise/bonus" → one-time + ongoing reallocation
  • "Should I pay off X or invest?" → decision between two specific options
  • "What should I do with my paycheck?" → recurring monthly allocation
  • "Got a tax refund" → one-time windfall

Step 2: Gather Current State

# Account balances (cash + debt)
sqlite3 data/finance.db "
SELECT name, mask, type, balance_current, balance_limit
FROM accounts
WHERE balance_current != 0
ORDER BY type, balance_current DESC;"
# Monthly income (average of last 3 months)
sqlite3 data/finance.db "
SELECT ROUND(AVG(monthly_income), 2) as avg_monthly_income FROM (
  SELECT strftime('%Y-%m', date) as month, SUM(ABS(amount)) as monthly_income
  FROM transactions WHERE amount < 0
    AND date >= date('now', '-90 days')
    AND description NOT LIKE '%TRANSFER%'
    AND description NOT LIKE '%EPAYMENT%'
    AND description NOT LIKE '%AUTOPAY%'
  GROUP BY month
);"
# Monthly essential expenses (average of last 3 months)
sqlite3 data/finance.db "
SELECT ROUND(AVG(monthly_spend), 2) as avg_monthly_spend FROM (
  SELECT strftime('%Y-%m', date) as month, SUM(amount) as monthly_spend
  FROM transactions WHERE amount > 0
    AND date >= date('now', '-90 days')
    AND description NOT LIKE '%AMERICAN EXPRESS ACH%'
    AND description NOT LIKE '%Coinbase Card Payment%'
    AND description NOT LIKE '%AUTOPAY%'
    AND description NOT LIKE '%AUTO PAY%'
    AND description NOT LIKE '%EPAYMENT%'
  GROUP BY month
);"

Read the full file on GitHub · 267 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 · 267 lines · 112 tokens per session scan A 18ab5c17ea07

Subscribe to this mod's changes

next-dollar is a skill published in the GitHub repository weklund/fiduciary (10 stars, last pushed 2mo ago), licensed MIT. It adds 112 tokens to every session and 2,352 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

Budget Planner

Create, manage, and optimize budgets for projects, departments, and organizations with variance tracking and scenario planning.

eddiebelaval/squire · 23 tokens

financial-planner

Your Personal Finance Manager for Canadians — an AI financial planning partner that conducts thorough financial interviews, builds complete plans, generates interactive dashboards, and provides ongoing coaching. Use this skill whenever someone asks about budgeting, saving, investing, debt strategy, retirement…

cjpatten/canadian-finance-planner-skill · 156 tokens

Construction Estimator

Construction cost estimation, project budgeting, material takeoffs, and bid preparation for contractors and builders.

eddiebelaval/squire · 22 tokens

ecommerce-budgeting-forecasting

Build rolling operating budgets for marketing spend, inventory purchases, and operations with variance analysis, scenario modeling, and budget utilization alerts.

finsilabs/awesome-ecommerce-skills · 32 tokens

ynab-assign-money

Helps give every dollar a job — assigns unallocated Ready to Assign money to categories, funds underfunded goals, and sets up new categories or category groups. Use when the user says "I have money to assign", "help me budget this month", "what should I fund", "help me set up a new category", "organize my budget…

auzroz/ynab-mcp · 87 tokens

ynab-big-goal-savings-planner

Helps plan and fund a large, specific, one-time savings goal with a dollar target and timeline — house down payment, car, wedding, sabbatical. Use when a user says "I'm saving for a house down payment", "how much do I need to save monthly for X", "help me set a savings target with a deadline", or "I want to buy a car…

auzroz/ynab-mcp · 92 tokens