Best use case
payment-tracker-run is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Automatic payment tracking and follow-up
Teams using payment-tracker-run should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/payment-tracker-run/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How payment-tracker-run Compares
| Feature / Agent | payment-tracker-run | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Automatic payment tracking and follow-up
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Payment Tracker - Run
> Monitors outstanding invoices, tracks payment status, sends reminders
## When to use
- "check payments"
- "which invoices are overdue?"
- "payment status check"
- "run payment tracker"
- Manual trigger for immediate payment check
## How to execute
### Full run
```bash
cd $AGENTS_PATH/payment-tracker
python3 payment_tracker_agent.py
```
This will execute:
1. Load outstanding invoices from deals.csv
2. Calculate payment status (OK/DUE_SOON/OVERDUE/PENDING_INVOICE)
3. Enrich with client/company context
4. Generate Telegram notification
5. Create follow-up email drafts
6. Log activities to activities.csv
7. Git commit changes
### Dry-run (no changes)
```bash
python3 payment_tracker_agent.py --dry-run
```
- Analyzes all invoices
- Shows what would be sent
- Does NOT write to CSV
- Does NOT send Telegram
- Does NOT make git commit
### Without notifications
```bash
python3 payment_tracker_agent.py --no-notify
```
- Performs the check
- Logs activities
- Skips Telegram notification
### Test notification
```bash
python3 payment_tracker_agent.py --force-notify
```
- Sends Telegram even if there are no issues
- For testing notification setup
## Output
### Telegram Notification
Sent to Saved Messages ('me'):
```
**Payment Tracker Report**
Total outstanding: **$4,827 USD**
2 overdue, 1 due soon, 0 pending invoice
🔴 **OVERDUE**
• **INV-095** - Enterprise Corp
$XXX USD • 8 days overdue
Action: Email Alice
🟡 **DUE SOON**
• **INV-096** - Client D
$X,XXX USD • Due 2026-02-15 (5 days since invoice)
✅ **OK** (3 invoices on track)
```
### Follow-up Drafts
File: `$AGENTS_PATH/data/payment_followups/YYYY-MM-DD_followup_drafts.md`
Contains ready-made email drafts for overdue invoices.
### Activities Log
Entries in `sales/crm/activities.csv`:
- activity_id: `act-XXX`
- type: `note`
- subject: `Payment tracker: Invoice #INV-095 - OVERDUE`
- created_by: `payment-tracker-agent`
### Agent Log
JSON file: `$AGENTS_PATH/data/payment_tracker_log.json`
```json
{
"ts": "2026-02-12T10:00:00",
"outstanding_total": 4827,
"overdue_count": 2,
"due_soon_count": 1,
"pending_invoice_count": 0,
"notifications_sent": true,
"errors": []
}
```
## Scheduled Run
The agent runs automatically via launchd:
- **Schedule**: Daily at 10:00 AM (Mon-Fri)
- **Plist**: `~/Library/LaunchAgents/com.yourcompany.payment-tracker.plist`
### Load schedule
```bash
cp $AGENTS_PATH/payment-tracker/com.yourcompany.payment-tracker.plist ~/Library/LaunchAgents/
launchctl load ~/Library/LaunchAgents/com.yourcompany.payment-tracker.plist
```
### Unload schedule
```bash
launchctl unload ~/Library/LaunchAgents/com.yourcompany.payment-tracker.plist
```
### Check status
```bash
launchctl list | grep payment-tracker
```
### View logs
```bash
tail -f /tmp/payment-tracker-agent.log
tail -f /tmp/payment-tracker-agent-error.log
```
## Payment Terms
- **Known clients** (status=active): 7 days
- **New clients** (status=new): 14 days
- **DUE_SOON warning**: 3 days before deadline
- **Follow-up cadence**:
- DUE_SOON: reminder every 3 days
- OVERDUE: daily reminders
## Payment Categories
1. **OK**: Invoice on track (days <= payment_terms - 3)
2. **DUE_SOON**: Approaching deadline (payment_terms - 3 < days <= payment_terms)
3. **OVERDUE**: Missed deadline (days > payment_terms)
4. **PENDING_INVOICE**: Deal delivered but invoice not sent yet
## Troubleshooting
### Telegram not sending
```bash
# Test Telegram connection
cd $TG_TOOLS_PATH
python3 -c "from tg_utils.auth import get_client; import asyncio; asyncio.run(get_client())"
# Force notification
cd $AGENTS_PATH/payment-tracker
python3 payment_tracker_agent.py --force-notify
```
### Activities not logging
```bash
# Check CSV permissions
ls -la $CRM_PATH/activities.csv
# Check git status
cd $PROJECT_ROOT
git status
# Dry-run to see what would be logged
cd $AGENTS_PATH/payment-tracker
python3 payment_tracker_agent.py --dry-run
```
### Wrong payment terms
Edit constants in `payment_tracker_agent.py`:
```python
DEFAULT_PAYMENT_TERMS_KNOWN = 7
DEFAULT_PAYMENT_TERMS_NEW = 14
DUE_SOON_BUFFER_DAYS = 3
```
## Integration
### Upstream
- **Invoice Generator** (#17): creates invoice_date, invoice_number in deals.csv
- **Manual bank check**: owner updates paid_date when payment is received
### Downstream
- **Daily Briefing** (#14): can include payment tracker summary
- **Activity Logging** (#13): shares activities.csv
## Human Approval
- Agent does NOT send emails automatically
- Generates drafts for review
- Owner decides when and how to send follow-ups
## Rollback
### Stop agent
```bash
launchctl unload ~/Library/LaunchAgents/com.yourcompany.payment-tracker.plist
```
### Revert activity logs
```bash
cd $PROJECT_ROOT
git log --grep="payment tracker"
git revert <commit-hash>
```
### Clear agent log
```bash
rm $AGENTS_PATH/data/payment_tracker_log.json
```
## Related skills
- `invoice` - invoice creation (process #17)
- `log-activity` - manual CRM activity logging
- `daily-briefing` - morning briefing (process #14)
## Owner
Your Name (your@email.com)
Process ID: #18Related Skills
polymarket-copy-tracker
Analyze top Polymarket traders for copy trading. Use when asked to find best traders to copy, analyze trader performance/history, evaluate wallet PnL, discover high-ROI wallets, or research trader win rates on Polymarket. Supports Dune analytics, Polymarket Data API, and automated scoring.
payment-integration
Integrate Stripe, PayPal, and payment processors. Handles checkout flows, subscriptions, webhooks, and PCI compliance. Use PROACTIVELY when implementing payments, billing, or subscription features.
Financial Tracker
Track business income and expenses in structured CSV format. Categorize transactions, monitor cash flow, generate P&L summaries, and spot spending trends.
expense-tracker
Manage expense tracker bot — deploy, check expenses, export data, sync locally
deepwork-tracker
Track deep work sessions locally (start/stop/status) and generate a GitHub-contribution-graph style minutes-per-day heatmap for sharing (e.g., via Telegram). Use when the user says things like “start deep work”, “stop deep work”, “am I in a session?”, “show my deep work graph”, or asks to review deep work history.
competitor-price-tracker
Monitor competitor pricing pages and send alerts when prices change. Track discount patterns, promotional cycles, and pricing strategy shifts.
wemp-operator
> 微信公众号全功能运营——草稿/发布/评论/用户/素材/群发/统计/菜单/二维码 API 封装
zsxq-smart-publish
Publish and manage content on 知识星球 (zsxq.com). Supports talk posts, Q&A, long articles, file sharing, digest/bookmark, homework tasks, and tag management. Use when publishing content to 知识星球, creating/editing posts, uploading files/images/audio, managing digests, batch publishing, or formatting content for 知识星球.
zoom-automation
Automate Zoom meeting creation, management, recordings, webinars, and participant tracking via Rube MCP (Composio). Always search tools first for current schemas.
zoho-crm-automation
Automate Zoho CRM tasks via Rube MCP (Composio): create/update records, search contacts, manage leads, and convert leads. Always search tools first for current schemas.
ziliu-publisher
字流(Ziliu) - AI驱动的多平台内容分发工具。用于一次创作、智能适配排版、一键分发到16+平台(公众号/知乎/小红书/B站/抖音/微博/X等)。当用户需要多平台发布、内容排版、格式适配时使用。触发词:字流、ziliu、多平台发布、一键分发、内容分发、排版发布。
zhihu-post-skill
> 知乎文章发布——知乎平台内容创作与发布自动化