Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+21 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+18 agentsPersonal Budget & Spending Sanity Gate Skill
A neutral, non-advisory checkpoint for validating expense data, arithmetic, and spending rule consistency.
$4.99
Personal Budget & Spending Sanity Gate Skill
Example session with this skill installed
Check this entry against my rule to flag anything over $100: Bought a mechanical keyboard from Keychron for $145.50 on 2023-10-12. Also, check the math for these: $12.50, $44.00, $8.00. Total: $65.50.
- Read your context and instructions
- Compiled the personal budget
I have reviewed the proposed purchase against your rule and audited the provided arithmetic for the secondary list.
Spending Sanity Review
| Check Type | Input Data | Result |
|---|---|---|
| Rule Consistency | Threshold: $100.00 / Item: $145.50 | Triggered |
| Expense Formatting | Date: 2023-10-12 / Merchant: Keychron | Consistent |
| Arithmetic Audit | $12.50 + $44.00 + $8.00 | Issue Detected |
Scope checked: Rule consistency, Expense entry, and Arithmetic sanity.
Inputs used: $100.00 threshold, $145.50 purchase, and three line items ($12.50, $44.00, $8.00) with a stated total of $65.50.
Evidence & Calculations:
- The purchase of $145.50 exceeds your $100.00 review threshold by $45.50. The rule is triggered.
- The manual total provided ($65.50) does not match the sum of the items.
- Calculation: $12.50 + $44.00 + $8.00 = $64.50.
- Difference: $1.00 variance from your stated total of $65.50.
Uncertainties:
- None for the data provided.
Clarifying question:
- Is the $1.00 difference in the subtotal due to a missing fee or a typo in the line items?
Next steps
- Update the subtotal to $64.50 or identify the missing $1.00 entry.
- Proceed with your internal review process for the flagged $145.50 keyboard purchase.
Connects securely to your tools. The creator never sees your data.
About this skill
Personal finances often suffer from sloppy record-keeping and ignored self-imposed rules. This skill acts as a neutral logic gate for proposed spending and expense data, catching errors before they enter your tracking system.
What it does
- Expense entry validation identifies missing amounts, unclear merchants, or inconsistent date formats.
- Rule consistency checking flags when a proposed purchase triggers a user-defined threshold or constraint.
- Arithmetic verification re-calculates totals, subtotals, and differences to ensure data integrity.
- Record consistency review scans CSV excerpts or lists for duplicate rows and category label drift.
- Neutral summarization provides a factual overview of reviewed items and identified unknowns.
How it works
- Identify request by determining if the user wants an entry check, rule comparison, or arithmetic audit.
- Review data against supplied user rules or standard formatting requirements.
- Audit consistency to find mismatches between labels, currencies, or previous entries.
- Generate report using a structured layout that separates verified facts from possible issues.
Frameworks & tools
This skill is framework-agnostic and processes raw text, CSV excerpts, or structured transaction logs. It is designed for integration into chat-based personal assistants or CLI-based expense workflows.
Why this beats prompting it yourself
Generic prompts often devolve into unwanted financial advice or judgmental commentary. This skill is strictly constrained to neutral observations, ensuring calculations are verified without the AI trying to manage your life or recommend investments.
Use cases
- Audit a list of recent transactions for duplicate charges or missing categories.
- Verify if a large purchase violates a self-imposed "review above $X" rule.
- Reconcile a series of line items against a provided total to find math errors.
- Standardize merchant naming and date formats across manual expense entries.
Known limitations
Does not provide financial, tax, or investment advice. Cannot access live bank feeds or account balances. Users must supply the conversion rates for currency checks.
No financial or tax advice. Does not connect to banks. Arithmetic only; no affordability assessments. Requires user-supplied conversion rates.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 13 days ago
Permissions
No special permissions declared or detected