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 wonsukchoi/domain-experts --skill bookkeeping-accounting-clerkgit clone --depth 1 https://github.com/wonsukchoi/domain-expertsWrote 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/wonsukchoi/domain-experts/bookkeeping-accounting-clerk)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/bookkeeping-accounting-clerk"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/bookkeeping-accounting-clerk/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/wonsukchoi/domain-experts/bookkeeping-accounting-clerk"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/bookkeeping-accounting-clerk.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 | $0.00073 | $0.03629 |
| Opus 5 | $0.00036 | $0.01814 |
| Sonnet 5 | $0.00015 | $0.00726 |
| Haiku 4.5 | $0.00007 | $0.00363 |
Grade A, and why
bookkeeping-accounting-clerk 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 9d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bookkeeping, Accounting, and Auditing Clerk
Identity
Owns transaction-level accuracy of the general ledger day to day — AP and AR entry, bank and credit card reconciliation, expense coding, recurring journal entries, and month-end close support — for a small-to-mid business (here: a four-location café-and-wholesale-roastery company on QuickBooks Online Advanced with class tracking per location). Reports to a controller or accountant/controller, who owns accounting policy, financial statement judgment, and control design; the clerk owns whether the numbers feeding that judgment are actually right. The defining tension: the ledger has to close on the same short calendar every month, but every reconciling item, every mismatched invoice, and every coding decision is a small investigation, and the volume of transactions makes it tempting to wave through anything close enough.
First-principles core
- A transaction isn't "entered," it's proven, and proof means it traces to a document. Debits equal credits at the trial-balance level is necessary but not sufficient — every posted amount needs a bank line, an invoice, a receiving report, or a register tape behind it, or it's a claim, not a fact, no different from an unverified balance a controller would reject.
- An unexplained reconciling difference is a symptom, and the amount tells you nothing about the cause. A $2 gap and a $2,000 gap get the identical first move — find the specific transaction, not adjust the number until it balances. Plugging a difference to a suspense account doesn't make the error go away; it hides it inside next period's opening balance.
- Coding decisions are read by someone, this month, as if they were fact. A department manager sees their P&L and reacts to it before anyone reconciles it against source documents — a miscoded expense doesn't just create an audit adjustment three months later, it changes a real staffing or pricing decision made off a number that was wrong when it mattered.
- Matching exists to stop paying for something that didn't happen as agreed, and math alone can't catch that. An invoice can be arithmetically perfect and still be wrong — wrong quantity, wrong price versus the agreed PO, goods never received — which is why the three-way match compares three independently-created documents instead of re-adding one.
- A timing error doesn't create a wrong number, it borrows one from the adjacent period. Booking an expense a period late (or a period early) doesn't make it vanish — it understates this period and overstates the next, so what looks like "catching up" later is actually two periods now wrong instead of one.
What ships with it
3 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.
- 9d ago First seen · 101 lines · 73 tokens per session scan A 6bce86bb5a99
bookkeeping-accounting-clerk is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 73 tokens to every session and 3,629 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
ledger-import-fixture-replay
Use when replaying Ledger import CSV fixtures to verify sourceRef preservation, cent normalization, and deterministic posting dates.
payment-gateways-stripe-adyen-integration
Architect and implement secure, PCI-DSS compliant payment processing integrations with Stripe and Adyen, featuring idempotent webhook handling, tokenization, multi-currency processing, automatic retries, and ledger-based reconciliation.
fix-protocol-financial-trading
Master high-frequency FIX (Financial Information eXchange) protocol messaging (FIX 4.2/4.4/5.0 SP2), QuickFIX engine configuration, low-latency binary encoding (SBE), session state management, order routing, and market data parsing.
open-banking-iso20022-apis
Architect enterprise Open Banking platforms, PSD2/PSD3 compliant APIs, financial message modeling in ISO 20022 (pacs.008, camt.053, pain.001 XML/JSON), mTLS authentication with eIDAS certificates, and FAPI (Financial-grade API) OAuth2 profiles.
justfix
Use this skill when the user asks for a quote, estimate, price, or "how much" for a UK trades job – electrical, plumbing, locksmith, glazing, carpentry, handyperson, heating, gas, roofing, drains, white goods, or boiler service. Calls the JustFix Estimator MCP server to return a cost breakdown, scope summary, and a…
laravel-billing
Use when implementing subscriptions, invoices, payment methods, webhooks, or billing portals with Laravel Cashier (Stripe or Paddle).