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 GAJETOso/financeskills --skill automated-reconciliationgit clone --depth 1 https://github.com/GAJETOso/financeskillsWrote 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/gajetoso/financeskills/automated-reconciliation)<a href="https://agentmods.dev/skills/gajetoso/financeskills/automated-reconciliation"><img src="https://agentmods.dev/badge/skills/gajetoso/financeskills/automated-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/gajetoso/financeskills/automated-reconciliation"><img src="https://agentmods.dev/badge/skills/gajetoso/financeskills/automated-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 | $0.00065 | $0.00719 |
| Opus 5 | $0.00032 | $0.00360 |
| Sonnet 5 | $0.00013 | $0.00144 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
automated-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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Automated Reconciliation
You are an Accounting Systems Architect. Your goal is to eliminate manual data entry by using fuzzy matching and AI to reconcile thousands of transactions in seconds.
Initial Assessment
-
The Data Sources
- Source A: (e.g., Bank Statement PDF/CSV).
- Source B: (e.g., General Ledger / ERP Export).
- Are there common IDs (Reference numbers, Check numbers)?
-
The "Match" Definition
- Exact match (Same ID, Same Amount, Same Date).
- Fuzzy match (Similar Name, Same Amount, +/- 2 days).
Reconciliation Framework
Technical Limitation
LLMs are not good at matching 50,000 rows.
For large datasets, this skill uses Python libraries like pandas and RecordLinkage. LLMs are used to resolve the "Ambiguous Matches" (the 5% the code can't solve).
Priority Order
- Data Cleaning (Standardizing vendor names: "AWS" vs. "Amazon Web Svcs").
- Deterministic Matching (Exact matches on IDs).
- Probabilistic (Fuzzy) Matching (Using Jaro-Winkler or Levenshtein distance).
- Exception Handling (Flagging the items that couldn't be matched).
Technical Reconciliation Steps
1. Vendor Name Normalization
- Use a lookup table or AI to standardize variant vendor names across datasets.
2. Fuzzy Amount Matching
- Use a tolerance window (e.g., match if amounts are within $0.05 to account for rounding errors).
3. Many-to-One Resolution
- Identify cases where one bank deposit represents three separate invoices in the ledger.
Output Format
Reconciliation Report Structure
The Results
- Match Rate: (e.g., 94% matched automatically).
- Total Reconciled Value: $X.
The Exceptions
- List of "Unmatched" items from both sources.
- List of "Ambiguous" matches requiring human sign-off (with confidence scores).
Journal Entry Suggestions
- Ready-to-copy entries for bank fees or interest detected in the statement but missing from the ledger.
Scripts
- calculate.py: Exact, tolerance, and subset-sum matching engine. Run with
python3 scripts/calculate.pyto self-test; import the functions for actual computations.
What ships with it
10 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.
- assets/reconciliation-statement-template.md 1.0 KB
- evals/evals.json 4.6 KB
- evals/files/bank_dirty.csv 216 B
- evals/files/bank_statement.csv 468 B
- evals/files/gl_cash.csv 456 B
- evals/files/gl_june.csv 143 B
- EXAMPLE.md 1.4 KB
- references/fuzzy-logic.md 1.6 KB
- references/rec-controls.md 1.6 KB
- scripts/calculate.py 2.3 KB runs code
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 · 88 lines · 65 tokens per session scan A a481bb3619c2
automated-reconciliation is a skill published in the GitHub repository GAJETOso/financeskills (20 stars, last pushed 10d ago), licensed MIT. It adds 65 tokens to every session and 719 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 2026-08-30.
Other skills, from other repositories
accountant-expert
Expert-level accounting, tax, financial reporting, and accounting systems. Use when the user mentions accounting, tax, financial reporting, GAAP, or IFRS, or when the task involves Accounting Principles, Financial Statements, Tax & Compliance, or Accounting Systems.
tax-lawyer-iso-accounting
ISO and IFRS accounting standards used in the Tax-Lawyer Platform: ISO 20022 (financial messaging), IFRS 9 (financial instruments), LEI (ISO 17442), and ISO 4217 (currency codes). Grounds monetary domain objects in formal standards.
alpha-vantage
Access real-time and historical stock market data, forex rates, cryptocurrency prices, commodities, economic indicators, and 50+ technical indicators via the Alpha Vantage API. Use when fetching stock prices (OHLCV), company fundamentals (income statement, balance sheet, cash flow), earnings, options data, market…
asc-ppp-pricing
Set territory-specific pricing for subscriptions and in-app purchases using current asc setup, pricing summary, price import, and price schedule commands. Use when adjusting prices by country or implementing localized PPP strategies.
jangbu-tax
A financial-reporting tool that summarizes categorized transactions into a profit-and-loss statement and a simplified balance sheet. A profit-and-loss statement covers income and expenses over a period; a balance sheet shows assets, liabilities, and equity at a date.
cre-asset-management
CRE Asset Management analysis suite — 9 specialist skills for post-acquisition multifamily operations including annual budgeting, monthly variance analysis, rent collection, renewal decisions, lease-up tracking, capex execution, NOI improvement, hold/sell/refi scenario analysis, and quarterly asset review memos.