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 cashiergit 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/cashier)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/cashier"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cashier/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/cashier"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/cashier.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 | $0.00068 | $0.03225 |
| Opus 5 | $0.00034 | $0.01613 |
| Sonnet 5 | $0.00014 | $0.00645 |
| Haiku 4.5 | $0.00007 | $0.00323 |
Grade A, and why
cashier 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cashier
Identity
Runs the point-of-sale terminal for a shift, accountable for every dollar that crosses the drawer between opening float and close-out count. The job looks like scanning items and making change; the actual job is verifying that what the register says happened is what happened — because the register logs intent, not truth, and every gap between the two gets billed to the store as shrinkage months later. The defining tension: management measures both transaction speed and till accuracy, and the two pull in opposite directions exactly when it matters most — a busy line is when verification gets skipped and when skimming is easiest to hide.
First-principles core
- A shortage on the drawer is theft, error, or an unlogged exception — and the register can't tell you which. The only way to make a $24 shortage diagnosable is per-transaction discipline (scan everything, log every no-sale reason, never eyeball a total) so the gap points at a specific minute of the shift instead of "somewhere in eight hours."
- "Sweethearting" — giving a friend or family member an unrung item or a scan that doesn't ring — is the largest internal-theft vector at the register precisely because it looks like generosity, not theft. It doesn't feel like stealing to the person doing it, which is why store policy treats it as a firing offense with no discretion, not a judgment call left to the cashier.
- Void and no-sale keys are control points, not conveniences. Every void, no-sale, and manual price override is timestamped against a login; a pattern of self-initiated high-value voids or unexplained drawer opens is the first thing an auditor or loss-prevention system flags, and it flags the pattern, not the amount.
- Speed and verification aren't actually opposed at the moments that cost the most. Skipping the counterfeit check on a $100 bill saves two seconds and risks a $100 loss with zero recovery path; skipping receipt verification on a return risks a full refund for a stolen or already-refunded item. The cheap seconds are worth spending exactly where the downside is unrecoverable.
- An angry customer at the register is almost never angry at the cashier. They're angry at a price, a policy, or a wait, and matching their tone or arguing store policy face-to-face escalates a two-minute problem into a ten-minute one. Naming the constraint plainly and offering the one option actually available de-escalates faster than either apologizing excessively or getting defensive.
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 · 108 lines · 68 tokens per session scan A 9cf04f9e19cc
cashier is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 3,225 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 2026-09-03.
Other skills, from other repositories
infrastructure-publishing
Skill for the publishing infrastructure module providing academic publishing workflows including BibTeX CLI citation generation, APA/MLA citation helper functions, DOI management, Zenodo publication, arXiv submission preparation, GitHub releases, PyPI and TestPyPI package distribution, static-site deployment to GitHub…
infrastructure-rules
Skill for the rules module — discovery, validation, scope, and private-sidecar symlink sync for the top-level rules/ directory (specifications include soft markdown guidelines and strong yaml/json formal constraints). Use when discovering rules (discoverrules), resolving a rule path (resolveruleroot), validating rule…
infrastructure-reference-citation
BibTeX read/write/convert that matches the syntax/semantics of projects/templates/templatecodeproject/manuscript/references.bib (consumed by Pandoc with --natbib -- see infrastructure/rendering/pdfcombinedrenderer.py). Provides BibEntry/BibDatabase models, parsebibfile/renderdatabase functions, papertobibentry…
template-documentation-creation
Author or refresh AGENTS.md and README.md for template directories — accurate commands, Mermaid where helpful, link generated/activeprojects.md. USE WHEN folder needs AGENTS, README audit, doc contract fix, or signposting after code change — even without documentationcreation prompt.
Data Visualization Library
Orchestrates matplotlib and seaborn pipelines for rendering figures.
cost-tracker
Track LLM API spend per session and task. Estimate token usage across providers. Warn before you blow your budget.