bank-statement-parsing

bank-statement-parsing is a skill for Claude Code, Codex from johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction. It costs 23 tokens per session (209 once invoked), scanned A, original, Apache-2.0.

A procedure for reading bank-statement PDFs with layout detection, optical character recognition (OCR), and a language model, then producing transaction records.

In plain words
What is it for?
Use it to extract dates, exact descriptions, debits, credits, opening balances, closing balances, and running balances from bank statements.
Why use it?
It reduces errors caused by unclear columns by checking each transaction against how the running balance changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract dates, exact descriptions, debits, credits, opening balances, closing balances, and running balances from bank statements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing
Install

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.

Any agent
npx skills add johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction --skill bank-statement-parsing
Clone the repo
git clone --depth 1 https://github.com/johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for bank-statement-parsing

README.md
[![agentmods](https://agentmods.dev/badge/skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing/github.svg)](https://agentmods.dev/skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing)
Your own site
<a href="https://agentmods.dev/skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing"><img src="https://agentmods.dev/badge/skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for bank-statement-parsing

Your own site · 80×15
<a href="https://agentmods.dev/skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing"><img src="https://agentmods.dev/badge/skills/johnsonhk88/ai-bank-statement-document-automation-by-llm-and-personal-finanical-analysis-prediction/bank-statement-parsing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 209 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00209
Opus 5 $0.00012 $0.00105
Sonnet 5 $0.00005 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured 12d ago against content hash 81134a9e57c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

bank-statement-parsing 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 12d 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.

agents/crewai/skills/bank-statement-parsing/SKILL.md · 21 lines

What it actually says

Bank Statement Parsing Skill

Core Rules

  • Always start by calling the PDF Extractor tool.
  • Do not trust "Paid In" / "Paid Out" column headers when they are ambiguous.
  • Verify every transaction by checking how the running Balance changes:
    • If Balance increases → Credit (Paid In)
    • If Balance decreases → Debit (Paid Out)
  • Extract Opening Balance from "Balance Brought Forward".
  • Extract Closing Balance from the final running balance in the transactions.
  • Preserve original descriptions exactly. Do not summarize or shorten them.
  • If column alignment in the extracted text is messy, rely on balance math rather than position.

Expected Output

Return transactions in a consistent structure with: Date, Description, Debit, Credit, Balance.

Changes

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.

  1. 12d ago First seen · 21 lines · 23 tokens per session scan A 81134a9e57c6

Subscribe to this mod's changes

bank-statement-parsing is a skill published in the GitHub repository johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction (627 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 23 tokens to every session and 209 once invoked, about $0.0001 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 2026-08-30.

Related

Other skills, from other repositories

report-generator

Generate professional HTML/PDF investment reports with interactive visualizations.

yennanliu/InvestSkill · 11 tokens

receipts-to-expenses

Read a batch of receipt images directly via vision, classify each into expense categories, optionally reconcile against a bank statement CSV, and produce a multi-sheet Excel workbook + a PDF summary. Use when given receipt photos and asked for an expense report.

skrun-dev/skrun · 54 tokens

financial-expense-automation

An expense-receipt workflow that reads PDF and image attachments, extracts their details, checks whether they are valid expense receipts, and records them in Feishu Bitable, a cloud table service.

DjangoPeng/agentic-ai · 100 tokens

pdf-invoice-extractor

OCR a PDF invoice with mistralocr and extract structured line-item data (vendor, date, amounts, VAT) for accounting reconciliation. Use when the user provides an invoice PDF to process.

Swih/mistral-mcp · 39 tokens

deepread-bank-statements

Extract structured data from bank statements — account holder, period, opening/closing balances, and every transaction as typed JSON. Works on PDF and scanned statements from any bank. Per-field confidence flags. PII redaction for compliant sharing. Free 2,000 pages/month.

deepread-tech/skills · 61 tokens

deepread-purchase-orders

Extract structured data from purchase orders — PO number, buyer/supplier, line items, quantities, prices, delivery dates, totals — as typed JSON. 2-way/3-way match against invoices. Per-field confidence flags. Free 2,000 pages/month.

deepread-tech/skills · 59 tokens