Expense Tracker Agent Skill for Openclaw

A scheduled, AI-driven daily expense tracker that processes Telegram check-ins, deduplicates entries, and syncs local Markdown ledgers with Google Sheets.

hohobohan
v1.0.0
Jun 3, 2026
0
544
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install hobohan-expense-tracker

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install hobohan-expense-tracker using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Expense Tracker Agent Skill?

The Expense Tracker skill empowers developers to automate daily personal finance logging using cron-scheduled AI agents. Built with a focus on ease of use and reliability, this skill prompts users via Telegram at key intervals throughout the day to record spending. It processes these micro-logs using the deepseek/deepseek-v4-flash model, ensuring intelligent categorization, deduction logic, and formatting.

Instead of relying on heavy third-party SaaS tools, this skill maintains local ownership of your financial data by writing directly to simple Markdown files. Simultaneously, a synchronization engine pushes these updates to a centralized Google Sheet, offering the perfect blend of local file-based privacy and cloud-based convenience. If you want to optimize your financial workflows with Openclaw Skills, this agent provides a highly customizable template for secure ledger management.

Expense Tracker Agent Skill Use Cases

  • Automated Expense Tracking: Log morning coffees, commutes, meals, and utilities directly through active Telegram notifications instead of manual data entry.
  • Data Decentralization: Keep a robust, human-readable local history of your daily expenses in simple Markdown ledger formats.
  • Multi-platform Expense Syncing: Sync localized developer ledgers with shared family or business Google Sheets automatically.
  • Historical Financial Audits: Reconstruct missing ledger files by backfilling data programmatically from sheet rows.

How Expense Tracker Agent Skill Works

  1. Cron Check-in Triggers: Cron jobs trigger deepseek-powered check-ins at 10:00 AM, 1:30 PM, and 10:00 PM to capture spending from different parts of the day.
  2. AI Inference & Deduction: The model processes the natural language response, categorizing the expense, extracting the dollar amount, and adhering to strict duplicate checking rules.
  3. Local Ledger Formatting: Verified entries are appended to a date-stamped file in the ledger/YYYY-MM-DD.md directory with the format - Category $Amount | Notes.
  4. Google Sheets Sync: Every morning at 9:30 AM, a dedicated script reads the local Markdown entries, normalizes the data, avoids duplicate key collisions, and appends new transactions to Google Sheets.

Expense Tracker Agent Skill Setup

Prerequisites

  • A Google Service Account JSON key saved at /home/hobopi/.openclaw/secrets/google-service-account.json.
  • Access to a Telegram bot paired with your Openclaw environment.

Step 1: Workspace Setup

Ensure the execution scripts are in your local workspace:

mkdir -p scripts ledger
# Copy sync-ledger-to-sheet.py and gen-expense-data.py into scripts/

Step 2: Configure Cron Triggers

Setup your cron prompts to fire at scheduled times using Openclaw Skills integrations:

# Morning Check-in (10am)
openclaw schedule "Morning spend (coffee, breakfast, transport)" --cron "0 10 * * *" --model deepseek/deepseek-v4-flash

# Sync script (9:30am daily)
openclaw schedule "python3 scripts/sync-ledger-to-sheet.py" --cron "30 9 * * *"

Expense Tracker Agent Skill Data Schema & Taxonomy

Ledger File Schema

All expense items are stored locally in Markdown files named chronologically.

Path: ledger/YYYY-MM-DD.md
Syntax: - Category $Amount | Notes

Approved Expense Categories

Category Description Example
Food & Drinks Daily snacks, coffees, dining out Breakfast bagel, coffee
Groceries Large-scale supermarket bulk shopping Weekly household run
Transportation Commuting, trains, ride shares Metro card reload, Uber
Household/Utilities Rent, electricity, home goods Monthly internet bill
Pet Pet food, vet bills, toys Kibble
Shopping Retail purchases, clothes, electronics New keyboard
Entertainment Movies, concerts, subscriptions Streaming services
AI Developer API costs, hosting, AI tools Netlify subscription
Other Anything not fitting above criteria Custom notes

Expense Tracker Agent Skill Advanced Features

  • Intelligent Deduplication Engine: Parses localized ledger lines to build dedup keys based on dates and normalized amounts, completely preventing double-logging.
  • Specialized Transport Check-in: Runs a secondary query every morning at 9:00 AM asking explicitly for the previous day's travel expenses to ensure accurate logging.
  • Historical Backfill Script: Queries existing Google Sheet rows to reconstruct missing physical ledger files programmatically.
  • Dashboard Ready Export: Generates normalized JSON files from local ledger data using scripts/gen-expense-data.py to power custom front-end visualization panels.
  • Highly Targeted Model Isolation: Enforces specific timeouts (up to 600s for late-night summaries) and pins execution to deepseek/deepseek-v4-flash to ensure high speeds and low overhead cost.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*