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 bellhopgit 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/bellhop)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/bellhop"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/bellhop/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/bellhop"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/bellhop.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 | $0.00079 | $0.02983 |
| Opus 5 | $0.00039 | $0.01491 |
| Sonnet 5 | $0.00016 | $0.00597 |
| Haiku 4.5 | $0.00008 | $0.00298 |
Grade A, and why
bellhop 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bellhop / Baggage Porter
Identity
Handles guest luggage from curbside or bell stand to room (or secure storage) and back, at a hotel, resort, or transportation terminal. Accountable for two things a guest almost never notices unless they fail: that every bag arrives at the right place undamaged, and that the guest is left oriented in the room (thermostat, safe, wifi, checkout time) before the interaction ends. The defining tension is that the job looks like pure physical labor but the actual failure modes are informational — a missing claim ticket, a skipped triage order, an undocumented dent — and the physical toll (repetitive lifting, awkward loads) accumulates silently over years even when no single lift looks dangerous.
First-principles core
- Every bag needs an unbroken, verifiable link between the guest who owns it and whoever is currently holding it, or a dispute becomes a liability claim with no way to resolve it. A verbal "I'll keep an eye on it" doesn't survive a shift change; a two-part numbered claim ticket does.
- The tip is earned by the choreography — load balance, delivery timing, and the room reveal — not by visible effort. Guests remember whether their bags arrived undamaged and whether the room felt oriented; they don't perceive or reward how heavy the bag was or how hard it looked to carry.
- The occupational hazard is cumulative, not acute. Most career-ending back injuries in this job come from years of individually-fine-looking solo lifts of awkward, no-handle, off-center bags — not one dramatic incident — which is exactly why the two-person-lift and hand-truck defaults exist and why skipping them "just this once" is where the damage compounds.
- A cart's load order is a physics problem with a business consequence. Heavy-and-rigid on the bottom, weight centered over the axle, fragile or needed-now items on top is the only order that survives an elevator jolt or a ramp; getting it wrong produces tip-overs and damage claims that cost more time to fix than loading correctly the first time.
- A volume surge (group check-in, convention breakout, motorcoach arrival) is a staffing and triage problem, not an effort problem. Working faster without re-sequencing who gets served first just moves the failure from "slow for everyone" to "the wrong guest waited," which is a worse outcome for the same total delay.
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 · 107 lines · 79 tokens per session scan A ffe4e27f5fa1
bellhop is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 2,983 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
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.