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 JoelLewis/finance_skills --skill reconciliationgit clone --depth 1 https://github.com/JoelLewis/finance_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/joellewis/finance_skills/reconciliation)<a href="https://agentmods.dev/skills/joellewis/finance_skills/reconciliation"><img src="https://agentmods.dev/badge/skills/joellewis/finance_skills/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/joellewis/finance_skills/reconciliation"><img src="https://agentmods.dev/badge/skills/joellewis/finance_skills/reconciliation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 225 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00117 | $0.06604 |
| Opus 5 | $0.00059 | $0.03302 |
| Sonnet 5 | $0.00023 | $0.01321 |
| Haiku 4.5 | $0.00012 | $0.00660 |
Grade A, and why
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 — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reconciliation
Core Concepts
1. Reconciliation Types and Hierarchy
Reconciliation is the systematic comparison of records across two or more systems to identify and resolve discrepancies. In securities operations, reconciliation ensures that the firm's internal records (the investment book of record, or IBOR) match the custodian's official records (the official book of record, or OBOR) and, where applicable, the clearing firm's records. The reconciliation hierarchy proceeds from the most fundamental data element (positions) through increasingly derived data elements.
Position Reconciliation. The foundational reconciliation. Compares the number of shares or units held for each security in each account between the firm's portfolio management system (PMS) and the custodian. Position reconciliation is typically zero-tolerance: any share count difference, no matter how small, constitutes a break. Fractional share differences (common with dividend reinvestment plans) must also be identified and resolved. Position reconciliation is performed daily, using end-of-day files from the custodian compared against the PMS position ledger.
Cash Reconciliation. Compares cash balances between the PMS and the custodian, accounting for settled cash, pending settlements, accrued income, and pending fee debits. Cash reconciliation is more nuanced than position reconciliation because timing differences are inherent — a trade executed on day T settles on T+1, and the PMS and custodian may record the cash impact on different dates. Cash tolerance thresholds are common, typically a small dollar amount (e.g., $0.50 to $5.00) to accommodate rounding differences across systems. Balances outside the tolerance require investigation.
Transaction Reconciliation. Compares individual transactions (trades, dividends, interest payments, transfers, fees) recorded in the PMS against the custodian's transaction ledger. Transaction reconciliation operates at the trade level, matching on security, quantity, price, trade date, and settlement date. Unmatched transactions on either side constitute breaks. Transaction reconciliation is typically performed on a T+1 basis — comparing yesterday's activity after the custodian's end-of-day file is received.
What ships with it
1 file 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 · 246 lines · 117 tokens per session scan A de9c847b7ab2
reconciliation is a skill published in the GitHub repository JoelLewis/finance_skills (184 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 6,604 once invoked, about $0.0006 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
stock-liquidity
Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth, market impact estimates, and turnover ratios via Yahoo Finance data. Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread, market depth, volume analysis, slippage, market impact, turnover ratio, or how…
fintel-data
Query Fintel (fintel.io) institutional market intelligence via the REST API at https://api.fintel.io/v1 with FINTELAPIKEY (X-API-KEY header), or the official MCP server at https://mcp.fintel.io/mcp. Read-only data: short interest, borrow rate/fee and shares available to borrow, daily short volume, fails-to-deliver…
estimate-analysis
Deep-dive into analyst estimates and revision trends for any stock using Yahoo Finance data. Use when the user wants to understand analyst estimate direction, how EPS or revenue forecasts changed over time, compare estimate distributions, or analyze growth projections across periods. Triggers: "estimate analysis for…
earnings-preview
Generate a pre-earnings briefing for any stock using Yahoo Finance data. Use this skill whenever the user wants to prepare for an upcoming earnings report, understand what analysts expect, review a company's beat/miss track record, or get a quick overview before an earnings call. Triggers include: "earnings preview…
earnings-recap
Generate a post-earnings analysis for any stock using Yahoo Finance data. Use when the user wants to review what happened after earnings, understand beat/miss results, see stock reaction, or get an earnings recap. Triggers: "AAPL earnings recap", "how did TSLA earnings go", "MSFT earnings results", "did NVDA beat…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…