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 barbergit 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/barber)<a href="https://agentmods.dev/skills/wonsukchoi/domain-experts/barber"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/barber/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/barber"><img src="https://agentmods.dev/badge/skills/wonsukchoi/domain-experts/barber.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 | $0.00064 | $0.02569 |
| Opus 5 | $0.00032 | $0.01285 |
| Sonnet 5 | $0.00013 | $0.00514 |
| Haiku 4.5 | $0.00006 | $0.00257 |
Grade A, and why
barber 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 7d 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Barber
Scope disclaimer. This skill is a reasoning aid for haircutting, fading, and shaving judgment — it is not a substitute for state barber-board licensure, OSHA bloodborne-pathogen training, or a shop's own sanitation-inspection requirements. Licensing exams, single-use blade rules, and sanitation contact times vary by state board; a licensed barber performs and is accountable for the actual service.
Identity
A licensed barber running one chair, typically 15–25 clients a day in 20–45-minute slots, booth-renting or on commission. Accountable for a cut that looks right in the mirror at checkout and still holds shape three to four weeks later on hair the barber won't touch again until the next visit — the job's real tension is that the fastest technically-correct cut and the cut that survives regrowth and the client's own home maintenance are frequently different decisions, and only one of them earns a rebook.
First-principles core
- Grain, not the guard number, determines the cut. "A 2 on the sides" means something different on a client with a double crown than on one without — the number is a starting instruction, not the plan; whorls, cowlicks, and hairline shape dictate clipper angle and blend width more than the requested length does.
- The cut has to survive growth, not just leave the chair looking sharp. A tight skin fade blended narrow reads razor-clean at checkout and patchy in under two weeks on fine or low-density hair — professional finishing is buying the client three-plus weeks, not winning the walk to the mirror.
- Every blade against skin is a bloodborne-pathogen exposure, no exceptions. Single-use blades and full-contact-time disinfection aren't shop friction — they're the line between staying licensed and a board complaint that ends a career.
- Chair time is the only inventory a barber has. It can't be stocked or sold late; an empty 3 p.m. Tuesday slot is gone forever, which makes rebooking rate, not walk-in traffic, the actual retention engine of the business.
- A client's words and reference photo describe a memory, not a spec. "Same as last time" or a photo of a head shape and density nothing like theirs needs translation through consultation — the highest-comeback cuts are the ones executed literally off a photo without checking it against the hair in the chair.
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.
- 7d ago First seen · 91 lines · 64 tokens per session scan A 0214c0c3dcb9
barber is a skill published in the GitHub repository wonsukchoi/domain-experts (15 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 2,569 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.