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 agentmods add skills/builderced/agent-skills/invoice-processingnpx skills add BuilderCed/agent-skills --skill invoice-processinggit clone --depth 1 https://github.com/BuilderCed/agent-skillsWhat 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 | $0.00032 | $0.00859 |
| Opus 5 | $0.00016 | $0.00430 |
| Sonnet 5 | $0.00006 | $0.00172 |
| Haiku 4.5 | $0.00003 | $0.00086 |
Grade A, and why
invoice-processing 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invoice Processing
When to Use
- Extracting data from PDF invoices
- Validating Factur-X or UBL structured invoices
- Classifying invoices by type, vendor, or account
- Detecting anomalies (duplicates, unusual amounts, missing fields)
- Mapping invoice fields to accounting entries
Extraction Pipeline
1. INPUT: PDF / Factur-X / UBL / image
2. DETECT FORMAT: structured XML embedded? → parse directly
No XML? → OCR + field extraction
3. EXTRACT FIELDS: map to canonical schema
4. VALIDATE: required fields, amounts, VAT consistency
5. CLASSIFY: expense category, accounting account, vendor
6. OUTPUT: structured JSON + confidence scores
Canonical Invoice Schema
{
"invoice_number": "FA-2026-042",
"invoice_date": "2026-04-15",
"due_date": "2026-05-15",
"supplier": {
"name": "Fournisseur SAS",
"tax_id": "FR12345678901",
"address": "12 rue Example, 75001 Paris"
},
"buyer": {
"name": "Client SARL",
"tax_id": "FR98765432109"
},
"lines": [
{
"description": "Prestation conseil",
"quantity": 5,
"unit_price": 200.00,
"vat_rate": 20.0,
"line_total": 1000.00
}
],
"subtotal": 1000.00,
"vat_amount": 200.00,
"total": 1200.00,
"currency": "EUR",
"payment_terms": "30 jours net"
}
Validation Rules
| Rule | Check | Severity |
|---|---|---|
| Required fields | invoice_number, date, supplier, total | Critical |
| Math consistency | sum(lines) = subtotal, subtotal + VAT = total | Critical |
| VAT rate validity | Rate matches country standard rates | Warning |
| Duplicate detection | Same number + supplier + amount | Critical |
| Date logic | due_date >= invoice_date | Warning |
| Currency | Valid ISO 4217 code | Warning |
Anomaly Detection
| Anomaly | Signal | Action |
|---|---|---|
| Duplicate invoice | Same number + supplier + amount +/- 5% | Block, flag for review |
| Round amount | Total is exact round number (1000, 5000) | Flag (common in fraud) |
| Weekend/holiday date | Invoice dated on non-business day | Flag |
| Unusual amount | > 3 standard deviations from vendor average | Flag for review |
| Missing VAT | Taxable transaction with 0% VAT | Flag, check exemption |
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.
- 2d ago First seen · 106 lines · 32 tokens per session scan A f7934ab0f09f
invoice-processing is a skill published in the GitHub repository BuilderCed/agent-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 859 once invoked, about $0.0002 per session on Opus 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
iflytek-ocr-invoice
Use when user asks to recognize invoices, extract receipt data, or OCR bills and tickets. Recognize and extract structured data from invoices, receipts, and bills using iFlytek OCR API (科大讯飞票据识别). Supports VAT invoices, taxi receipts, train tickets, toll invoices, medical bills, bank receipts, and more.
financial-report-analysis
Analyze company annual reports, quarterly reports, 10-K/10-Q filings, earnings releases, shareholder letters, or financial-report PDFs/URLs/files and produce a professional Chinese Markdown report for ordinary investors. Use when the user provides a company financial report address or local file and asks for 财报分析…
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
report-stock
Generate comprehensive stock analysis report (PDF or markdown) with trend, PMCC, and fundamental analysis.
procesar-mis-estados-de-cuenta
Proceso un lote de estados de cuenta bancarios y de tarjeta de crédito en PDF o CSV de principio a fin: extraigo cada transacción (subagentes Haiku en paralelo), normalizo los nombres de las contrapartes, categorizo contra tu plan de cuentas bloqueado (subagentes Sonnet en paralelo), detecto transferencias entre…
download-platform-invoices
Harvest monthly SaaS billing invoices into normalized records and official PDF files.