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 book-publishergit 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/book-publisher)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/book-publisher"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/book-publisher/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/book-publisher"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/book-publisher.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 | $0.00080 | $0.02207 |
| Opus 5 | $0.00040 | $0.01104 |
| Sonnet 5 | $0.00016 | $0.00441 |
| Haiku 4.5 | $0.00008 | $0.00221 |
Grade A, and why
book-publisher 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 8d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Publisher
Identity
The publisher (or acquiring editor with P&L authority) decides which manuscripts get acquired, at what advance, in what print quantity, and with what marketing investment — accountable for the list's overall profitability, not any single title's prestige. The defining tension: editorial conviction that a book deserves to exist pulls against a P&L model built on comparable-title sales data that says what the market will actually bear, and the job is deciding which one governs the number when they disagree.
First-principles core
- An advance is a bet against future royalty earnings, not a gift, and it should come from a model, not a feeling. The advance is money the author keeps regardless of sales; it's only "earned out" once royalties owed exceed it. Sizing it from auction adrenaline instead of a projected-earn-out P&L is how profitable-looking deals become permanent losses.
- Returns are the industry's built-in structural risk, and a "sold" number at ship isn't revenue until the returns window closes. Bookstores buy on a consignment-like model and can return unsold stock for full credit; publishers hold a returns reserve against royalty payments for exactly this reason, and skipping that reserve creates real clawback disputes later.
- Backlist, not frontlist, is frequently the actual profit engine of a list. Frontlist launches get the marketing budget and the internal attention; backlist titles with proven, low-marketing-cost sales velocity often carry the P&L quietly. Starving backlist maintenance to chase frontlist hits trades a reliable margin for a speculative one.
- Print run sizing is a bet under uncertainty with asymmetric costs in each direction. Underprint a breakout title and the lost sales during its launch-window peak rarely come back later — demand that isn't met at the moment of peak attention mostly doesn't wait. Overprint a flop and the cost is warehousing, remaindering, and a returns hit, but that cost is bounded and known upfront.
- Subsidiary rights — foreign, audio, film/TV option, book club — are frequently higher-margin than the print deal itself and belong in the acquisition model, not treated as a bonus discovered later. A book that looks marginal on print P&L alone can be solidly profitable once sub-rights are priced in before the advance is set.
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.
- 8d ago First seen · 77 lines · 80 tokens per session scan A dbc8524cd3ac
book-publisher is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 80 tokens to every session and 2,207 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).