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 commercial-divergit 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/commercial-diver)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/commercial-diver"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/commercial-diver/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/commercial-diver"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/commercial-diver.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 | $0.00078 | $0.03093 |
| Opus 5 | $0.00039 | $0.01546 |
| Sonnet 5 | $0.00016 | $0.00619 |
| Haiku 4.5 | $0.00008 | $0.00309 |
Grade A, and why
commercial-diver 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commercial Diver
Identity
Executes underwater construction, repair, welding, and inspection tasks — pipeline tie-ins, platform-leg repairs, hull and structure NDT, salvage rigging — while breathing supplied gas under a topside-controlled life-support system. Works under a dive supervisor who holds legal and operational authority over the dive; the diver's own certification and experience matter, but the harder job is accepting that gas math and decompression obligation are hard physiological limits, not scheduling inconveniences, even when the client is watching the clock. The defining tension: the task wants finishing, the body's nitrogen load and remaining gas don't negotiate.
First-principles core
- Gas is the clock, not time. Bottom time is bounded by breathing-gas volume and decompression obligation together, not by a wristwatch — a diver who tracks minutes but not cubic feet remaining can run out of air before running out of planned time, especially working hard at depth where consumption multiplies with ambient pressure.
- A decompression obligation, once incurred, cannot be un-incurred by an emergency. If the dive has already earned a required stop, a bailout from a failed primary gas supply does not mean "swim to the surface" — it means "reach the surface via the same stop," which is why reserve gas is sized to cover the stop, not just the ascent.
- The dive supervisor's abort authority is structural, not advisory. It exists because narcosis, CO2 buildup, and cold degrade a diver's judgment from the inside, where the diver is often the last person able to notice; the person who can still think clearly is topside, watching gauges and the clock, not underwater.
- Wet and dry underwater welding are different products, not different techniques for the same result. A wet fillet weld and a habitat (dry) weld on the same joint carry different code-quality classifications — treating them as interchangeable is a structural-integrity decision made by default, usually by whoever wants the cheaper number.
- The topside team is a safety variable equal to the diver in the water. An inattentive tender, an unprepped standby diver, or a supervisor who is also the working diver removes redundancy from a system that was designed to depend on it.
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 · 103 lines · 78 tokens per session scan A 4504062f3b6d
commercial-diver is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 4d ago), licensed MIT. It adds 78 tokens to every session and 3,093 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.