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.
npx skills add weklund/fiduciary --skill next-dollargit clone --depth 1 https://github.com/weklund/fiduciaryWrote 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/skills/weklund/fiduciary/next-dollar)<a href="https://agentmods.dev/skills/weklund/fiduciary/next-dollar"><img src="https://agentmods.dev/badge/skills/weklund/fiduciary/next-dollar/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/skills/weklund/fiduciary/next-dollar"><img src="https://agentmods.dev/badge/skills/weklund/fiduciary/next-dollar.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 | $0.00112 | $0.02352 |
| Opus 5.5 | $0.00045 | $0.00941 |
| Sonnet 5.5 | $0.00022 | $0.00470 |
| Haiku 4.5 | $0.00011 | $0.00235 |
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 2mo 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.
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
- Determine how much they're allocating (ask if not stated)
- Gather their current financial state
- Walk the order of operations, checking each step against reality
- Identify where THEY are in the sequence
- 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
);"
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.
- 2mo ago First seen · 267 lines · 112 tokens per session scan A 18ab5c17ea07
next-dollar is a skill published in the GitHub repository weklund/fiduciary (12 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 2,352 once invoked, about $0.0004 per session on Opus 5.5. 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.
Other skills, from other repositories
ecommerce-budgeting-forecasting
Build rolling operating budgets for marketing spend, inventory purchases, and operations with variance analysis, scenario modeling, and budget utilization alerts.
ynab-debt-payoff-planner
Helps build a sustainable debt-payoff plan that fits inside a real budget instead of fighting it. Use when a user says "help me pay off my credit cards", "snowball or avalanche, which should I do", "how do I set up a debt goal", "I keep going into debt for emergencies while paying off debt", or "what order should I…
ynab-first-budget-setup
Guides a brand-new YNAB user through structuring their first budget — category-group pattern, right level of detail, and avoiding beginner traps. Use when a user says "I just signed up for YNAB, where do I start", "how should I set up categories", "how many categories should I have", "should I track every subscription…
ynab-income-change-prep
Helps prepare financially for a known or likely upcoming income change — parental leave, job-loss risk, retirement transition, return to school — before it happens. Use when a user says "I'm going on parental leave, how do I prepare", "I might get laid off", "I'm planning to retire in a year", "how do I prepare for a…
ynab-irregular-income-planner
Teaches the budgeting approach for freelancers, commission earners, and gig workers with variable month-to-month income. Use when a user says "my income is different every month", "I'm a freelancer, how do I budget", "I don't know how much I'll make next month", "how do I stop overspending in good months", or "how…
ynab-monthly-review
Runs a complete end-of-month budget review — this month's performance vs. plan, goal progress, income/savings trend, net worth change, and suggested targets for next month. Use when the user says "let's do my monthly budget review", "end of month check-in", "how did this month go", "review my budget", "close out this…