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 jpeslar1/john-peslar-ai-skills --skill thesalonguy-hair-advisorgit clone --depth 1 https://github.com/jpeslar1/john-peslar-ai-skillsWrote 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/jpeslar1/john-peslar-ai-skills/thesalonguy-hair-advisor)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/thesalonguy-hair-advisor"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/thesalonguy-hair-advisor/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/jpeslar1/john-peslar-ai-skills/thesalonguy-hair-advisor"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/thesalonguy-hair-advisor.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 | $0.00070 | $0.00896 |
| Opus 5.5 | $0.00028 | $0.00358 |
| Sonnet 5.5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
thesalonguy-hair-advisor 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 18d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TheSalonGuy-Inspired Hair Advisor
Use this as a technical, hair-first decision lens. It is inspired by public educational work from Stephen Marinaro, known as TheSalonGuy, not a simulation of him. Read the source map when current source context or attribution matters.
Core lens
A haircut has to cooperate with growth direction, texture, density, bulk, and the head's visible shape. Product can refine a workable cut. It cannot reliably compensate for a shape that fights the hair.
Start with the relationship between top, corners, and sides. Do not prescribe a fade, a quiff, or a texture product before understanding where the hair gains width, collapses, or flips direction.
Use this skill for
- Choosing among keeping length, refining the current cut, or making a major change
- Turning photos and a desired look into a practical barber brief
- Troubleshooting why a style becomes round, bulky, flat, frizzy, or hard to control
- Building a realistic styling routine for wavy, curly, straight, thick, fine, or coarse hair
Workflow
- Gather what changes the decision: front, side, and back photos; hair clean and unstyled if possible; current styling routine; desired maintenance level; and whether the person wants to grow, maintain, or shorten.
- Describe only observable factors. Call out apparent texture, direction, bulk placement, crown behavior, side-to-top contrast, and whether the silhouette is balanced. Treat hairline and density conclusions as tentative from photos.
- Give three paths:
- Hold - what can be improved through styling alone.
- Refine - the smallest cut that makes the current direction intentional.
- Change - a different silhouette only if it solves a visible problem better.
- Recommend one path, explain the tradeoff, then give a barber brief that specifies the desired silhouette rather than relying on vague words such as "clean it up."
- Give a simple styling sequence: dampness level, directional blow-dry or air-dry choice, product type by function, amount, and finish. Recommend the fewest products that achieve the result.
What ships with it
1 file 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.
- 18d ago First seen · 80 lines · 70 tokens per session scan A 3ac88c97bb66
thesalonguy-hair-advisor is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 70 tokens to every session and 896 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-19.
thesalonguy-hair-advisor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| thesalonguy-hair-advisorjpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 70 | Claude Code |
| webgl-holographic-foilnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 41 | Claude Code, Codex |
| html-ppt-hermes-cyber-terminalnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 53 | Claude Code, Codex |
| html-ppt-taste-brutalistnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 78 | Claude Code, Codex |
| visual-ralphYeachan-Heo/oh-my-codex | Skill | 34k | 3d ago | MIT | A | 52 | Codex |
| glance-canonical-layoutsandroid/skills | Skill | 10k | yesterday | Apache-2.0 | A | 56 | Claude Code |
| accessibilitymicrosoft/hve-core | Skill | 1.6k | yesterday | MIT | A | 47 | Claude Code |