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 skills add Receiptor-AI/bookkeeping-skills --skill bank-reconciliationgit clone --depth 1 https://github.com/Receiptor-AI/bookkeeping-skillsWrote 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.
[](https://agentmods.dev/skills/receiptor-ai/bookkeeping-skills/bank-reconciliation)<a href="https://agentmods.dev/skills/receiptor-ai/bookkeeping-skills/bank-reconciliation"><img src="https://agentmods.dev/badge/skills/receiptor-ai/bookkeeping-skills/bank-reconciliation/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.
<a href="https://agentmods.dev/skills/receiptor-ai/bookkeeping-skills/bank-reconciliation"><img src="https://agentmods.dev/badge/skills/receiptor-ai/bookkeeping-skills/bank-reconciliation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.03002 |
| Opus 5 | $0.00029 | $0.01501 |
| Sonnet 5 | $0.00012 | $0.00600 |
| Haiku 4.5 | $0.00006 | $0.00300 |
Grade A, and why
bank-reconciliation 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.
How it starts
The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bank Reconciliation
Match recorded transactions against bank and credit card statements to verify the books are accurate, complete, and audit-ready.
Read these when needed
- Read references/MATCHING-RULES.md when deciding what can be auto-matched versus escalated.
- Run
scripts/reconciliation_summary.pywhen you already have reconciliation records and need a deterministic matched/unmatched summary.
Why reconciliation matters
The bank knows what actually happened. Your books reflect what you think happened. Reconciliation finds the gap between the two. Without it, you can't trust any number in your financial statements — not your cash balance, not your profit, not your tax liability.
Most small business accounting errors are discovered during reconciliation: duplicate entries, missed transactions, incorrect amounts, transactions booked to the wrong account, and timing differences between when you record something and when the bank processes it. The IRS expects reconciled books. An unreconciled set of books is one of the first things an auditor flags.
What you need
Two data sources, covering the same time period (usually one calendar month):
Book side — Your recorded transactions. Sources: accounting software export (QBO, CSV), spreadsheet ledger, or the output of receipt processing. If you don't have organized books, start with receipt processing. An email-native extraction tool can build a transaction list from inbox receipts much faster.
Bank side — The statement from your financial institution. Sources: CSV or OFX/QFX download from online banking (preferred — already structured), PDF statement (requires parsing), or a connected bank feed in your accounting software. Get the statement for the exact period you're closing. Partial-month statements create false discrepancies.
Step 1: Normalize both data sets
Before matching, get both sources into identical format:
| Field | Format | Notes |
|---|---|---|
date |
YYYY-MM-DD | Transaction date (not posting date if they differ) |
description |
String | Cleaned: remove extra whitespace, standardize merchant names |
amount |
Decimal, signed | Negative = money out (payments, withdrawals). Positive = money in (deposits, credits). |
reference |
String | Check number, transaction ID, or confirmation number if available |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 255 lines · 58 tokens per session scan A 075ef82e36b4
bank-reconciliation is a skill published in the GitHub repository Receiptor-AI/bookkeeping-skills (4 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 3,002 once invoked, about $0.0003 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
bookkeeping
Use when a small business needs audit-ready books — a chart of accounts, posting a transaction to the right account and side, clearing an uncategorized bank feed, cash vs accrual, or a ledger that won't tie to the bank. NOT interpreting the numbers — runway, burn, P&L cadence (that is finance-ops), NOT issuing…
correction-memory
A local memory system that stores tax-accountant corrections to transaction classifications. It matches future transactions to earlier vendor or description patterns.
nightly-batch
Batch-process all client companies overnight. Fetches unprocessed transactions from freee API, runs the full classification pipeline, and generates a summary for morning review.
tax-classifier
A system for assigning Japanese business transactions to accounting categories, called 勘定科目, and consumption-tax treatments. It checks exclusions, past corrections, keywords, and then uses AI when needed.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
monthly-closer
A monthly accounting report generator that summarizes transactions by account category and compares them with the previous month.