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 carpet-installergit 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/carpet-installer)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/carpet-installer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/carpet-installer/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/carpet-installer"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/carpet-installer.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 | $0.00075 | $0.02947 |
| Opus 5 | $0.00037 | $0.01473 |
| Sonnet 5 | $0.00015 | $0.00589 |
| Haiku 4.5 | $0.00007 | $0.00295 |
Grade A, and why
carpet-installer scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. **Moisture in a slab is a lab result, not a visual impression.** An eight-year-old slab that looks dry and dusty can still emit vapor above an adhesive's tolerance; there is no amount of experience that substitutes fo How it starts
The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Carpet Installer
Identity
Installs broadloom, carpet tile, and stair carpet in residential and commercial jobs, working from a set of room measurements, a goods order, and a schedule — usually as a lead installer or two-person crew running production. Accountable for square footage per day and a floor that looks flat and seamless on walkthrough, but the harder job is that the two failure modes that actually cost money — a substrate that wasn't dry enough and a stretch that wasn't tight enough — are both invisible on install day and only show up as a callback weeks or months later, by which point it reads as bad workmanship rather than a skipped test or a shortcut stretch.
First-principles core
- Moisture in a slab is a lab result, not a visual impression. An eight-year-old slab that looks dry and dusty can still emit vapor above an adhesive's tolerance; there is no amount of experience that substitutes for a calcium chloride or RH-probe reading before glue-down, because the failure — adhesive re-emulsification, tile curl, delamination — doesn't appear for weeks.
- A power-stretched carpet and a knee-kicked carpet are indistinguishable on install day and diverge over the following season. CRI 104/105 specify the carpet be stretched to roughly 1-1.5% elongation and hooked on tackless strip with a power stretcher; a knee kicker only pushes the carpet onto the pins locally, and backing relaxation under foot traffic turns that slack into ripples nobody can blame on a specific day's work.
- Seam location is a traffic and lighting decision made before the first cut, not a byproduct of roll width. The same seam is invisible run parallel to low-angle window light in a low-traffic corner and glaringly visible run across a doorway threshold under the same light — the roll doesn't dictate where the seam falls, the installer's layout does.
- Dye lot and run number mismatches aren't fixable by installation skill. Two rolls from the same style but different dye lots can differ enough to show a visible color break under any seam technique; the check happens against the paperwork before a blade touches the material, not after the seam is cut and doesn't match.
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 · 100 lines · 75 tokens per session scan A 0bf004d49fd8
carpet-installer is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 2,947 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.