arc-budget-tracker

Communication
v1.0.0
Benign

Track agent spending, set budgets and alerts, and prevent surprise bills.

496 downloads496 installsby @trypto1019

Setup & Installation

Install command

clawhub install trypto1019/arc-budget-tracker

If the CLI is not installed:

Install command

npx clawhub@latest install trypto1019/arc-budget-tracker

Or install with OpenClaw CLI:

Install command

openclaw skills install trypto1019/arc-budget-tracker

or paste the repo link into your assistant's chat

Install command

https://github.com/openclaw/skills/tree/main/skills/trypto1019/arc-budget-tracker

What This Skill Does

Tracks every transaction an agent makes, enforces spending limits, and warns before the budget runs out. Stores data locally in JSON and exposes commands for logging, checking, summarizing, and exporting expenses.

Blocks purchases before they happen rather than alerting after the bill arrives.

When to Use It

  • Logging API call costs after each agent task
  • Blocking a domain purchase that would exceed remaining budget
  • Reviewing daily spending by category before starting new work
  • Setting a hard cap before launching an autonomous agent
  • Exporting transaction history to CSV for monthly accounting
View original SKILL.md file
# Budget Tracker

Track every cent your agent spends. Set hard limits. Get alerts before you blow your budget.

## Why This Exists

Autonomous agents with access to APIs, domains, and services can rack up unexpected bills. This skill gives you a financial safety net — log every transaction, enforce spending limits, and always know exactly where you stand.

## Commands

### Log a transaction
```bash
python3 {baseDir}/scripts/budget.py log --amount 10.00 --merchant "Namecheap" --category "domain" --note "arcself.com registration"
```

### Check balance
```bash
python3 {baseDir}/scripts/budget.py balance
```

### View spending summary
```bash
python3 {baseDir}/scripts/budget.py summary
```

### View recent transactions
```bash
python3 {baseDir}/scripts/budget.py history --limit 10
```

### Set budget limit
```bash
python3 {baseDir}/scripts/budget.py set-budget --total 200.00
```

### Set alert threshold (warn when balance drops below this)
```bash
python3 {baseDir}/scripts/budget.py set-alert --threshold 50.00
```

### Check if a purchase is safe
```bash
python3 {baseDir}/scripts/budget.py check --amount 25.00
```

### Export to CSV
```bash
python3 {baseDir}/scripts/budget.py export --format csv
```

## Data Storage

Budget data is stored in `~/.openclaw/budget-tracker/budget.json` by default. Override with `--data-dir /path/to/dir`.

The JSON structure:
```json
{
  "budget": {"total": 200.00, "alert_threshold": 50.00},
  "transactions": [
    {
      "id": "txn_001",
      "timestamp": "2026-02-15T14:00:00Z",
      "amount": 10.00,
      "merchant": "Namecheap",
      "category": "domain",
      "note": "arcself.com"
    }
  ]
}
```

## Categories

Use consistent categories: `domain`, `hosting`, `api`, `tool`, `subscription`, `marketing`, `other`.

## Alerts

When balance drops below the alert threshold, the skill outputs a warning. When a purchase would exceed the remaining budget, it blocks and warns.

## Tips

- Log transactions immediately after spending — don't batch them
- Use `check` before any purchase to verify budget safety
- Run `summary` at the start of each day for awareness
- Set `--alert-threshold` to 25% of your total budget

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Logging API call costs after each agent task

AGENT
  1. 1Logging API call costs after each agent task
  2. 2Blocking a domain purchase that would exceed remaining budget
  3. 3Reviewing daily spending by category before starting new work
  4. 4Setting a hard cap before launching an autonomous agent
  5. 5Exporting transaction history to CSV for monthly accounting
OUTPUT
Track agent spending, set budgets and alerts, and prevent surprise bills.

Share this skill

Security Audits

VirusTotalBenign
OpenClawBenign
View full report

These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.

Details

LanguageMarkdown
Last updatedFeb 25, 2026