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 san-npm/skills-ws --skill accounting-financegit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/accounting-finance)<a href="https://agentmods.dev/skills/san-npm/skills-ws/accounting-finance"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/accounting-finance/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/san-npm/skills-ws/accounting-finance"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/accounting-finance.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 | $0.00096 | $0.06441 |
| Opus 5 | $0.00048 | $0.03220 |
| Sonnet 5 | $0.00019 | $0.01288 |
| Haiku 4.5 | $0.00010 | $0.00644 |
Grade A, and why
accounting-finance 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accounting & Finance
Not tax, legal, or audit advice. This skill encodes general operator practice and standard frameworks (US GAAP, IFRS, ASC 606/IFRS 15, EU VAT). Rates, thresholds, registration triggers, and filing rules change and are jurisdiction-specific. Before filing anything or relying on a number for a board, lender, investor, or tax authority, have it reviewed by a qualified accountant/tax advisor licensed in the relevant jurisdiction. Route any edge case — multi-state US nexus, cross-border digital services, equity/SAFE accounting, R&D capitalization, transfer pricing, M&A, or revenue-recognition judgment calls — to a professional. Treat every concrete rate/threshold below as "verify before use."
Sibling skills (don't duplicate — cross-link): country-level tax depth →
eu-tax-accounting(all 27 EU member states: corporate, VAT, payroll, deadlines). Billing/dunning/usage metering implementation →saas-billing(Express/Node) orstripe-billing(Next.js). Pricing/packaging →pricing-optimization. GTM funnel/forecasting →revenue-operations. Churn/retention cohort analysis →retention-analytics. EU regulatory (GDPR, contracts, entity) →eu-legal-compliance.
1. P&L Structure (GAAP / IFRS)
Standard multi-step income statement. Key rule: define what OpEx contains so D&A is counted exactly once. Below, operating expenses are stated excluding depreciation & amortization (the "ex-D&A" convention common in SaaS reporting); D&A is its own line. EBITDA then equals operating income + D&A with no double-count. If your accounting system buckets D&A inside OpEx, drop the separate D&A line and compute EBITDA = operating income + D&A (added back), not by re-subtracting it.
| # | Line item | Calculation | Watch for |
|---|---|---|---|
| 1 | Revenue (net) | Recognized per ASC 606/IFRS 15 (§6), net of refunds/credits | Recognized ≠ billed ≠ cash collected. Don't book deferred revenue as revenue. |
| 2 | COGS / Cost of revenue | Hosting/infra, third-party API/usage fees, payment processing, customer support & success delivery, onboarding/implementation labor | SaaS COGS typically 15–30% of revenue. Keep R&D and S&M out of COGS. |
| 3 | Gross profit | Revenue − COGS | SaaS target gross margin 70–85%. |
| 4 | Operating expenses (ex-D&A) | Sales & Marketing + Research & Development + General & Administrative | Allocate fully-loaded headcount (salary + employer taxes + benefits) to the right function. |
| 5 | EBITDA | Gross profit − OpEx(ex-D&A) | Proxy for operating cash generation; ignores capex, financing, tax. |
| 6 | Depreciation & amortization | Capitalized assets + capitalized software/intangibles amortization | Pure non-cash; never in COGS and here. |
| 7 | Operating income (EBIT) | EBITDA − D&A | GAAP operating result. |
| 8 | Net interest | Interest expense − interest income | |
| 9 | Pre-tax income (EBT) | EBIT − net interest ± other | |
| 10 | Income tax expense | Current + deferred tax | Tax expense (accrual) ≠ tax paid (cash). |
| 11 | Net income | EBT − income tax | Bottom line. |
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 · 313 lines · 96 tokens per session scan A 18c3af51c0fb
accounting-finance is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 5d ago), licensed MIT. It adds 96 tokens to every session and 6,441 once invoked, about $0.0005 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
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
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…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.
reading-receipt
An image-reading workflow for extracting structured information from receipts, invoices, and hometown-tax donation certificates. It can first extract text from PDFs and otherwise read their images.