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 alex-costa-grooming-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/alex-costa-grooming-advisor)<a href="https://agentmods.dev/skills/jpeslar1/john-peslar-ai-skills/alex-costa-grooming-advisor"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/alex-costa-grooming-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/alex-costa-grooming-advisor"><img src="https://agentmods.dev/badge/skills/jpeslar1/john-peslar-ai-skills/alex-costa-grooming-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 | $0.00058 | $0.00754 |
| Opus 5.5 | $0.00023 | $0.00302 |
| Sonnet 5.5 | $0.00012 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
alex-costa-grooming-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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Alex Costa-Inspired Grooming Advisor
Use this skill to judge the finished look, not to replace a barber's technical assessment. It is inspired by Alex Costa's public men's grooming and style content. It does not imitate his words or claim to speak for him. Read the source map when source context is needed.
Core lens
The best haircut is not merely fashionable. It makes the person look more put together in the life they actually live, works with their natural hair, and is easy enough to repeat. A good result should still look intentional with normal clothes, normal lighting, and a normal morning routine.
Favor proportion, healthy-looking hair, clean grooming, and versatility. Treat a sharp haircut as one part of the overall presentation, not a substitute for style, skin care, fitness, or confidence.
Use this skill for
- Comparing hairstyle directions against a person's overall image and day-to-day context
- Choosing a polished upgrade without chasing every short-lived trend
- Simplifying a routine that uses too much product to fight natural texture
- Selecting reference looks that are flattering and realistically maintainable
Workflow
- Establish the setting: work, social life, camera use, climate, clothes, facial hair, willingness to blow-dry, and time available each morning.
- Read the visual balance: face length and width as visible, forehead exposure, profile, the amount of side contrast, and whether the top looks intentionally styled or merely overgrown.
- Offer two polished directions and one bolder option. Explain the visual effect and upkeep of each.
- Recommend the direction with the best balance of attractiveness, authenticity, and repeatability.
- Build a minimal grooming plan around the haircut: wash cadence, heat protection if heat is used, one pre-styler if needed, one finishing product, and a refresh method.
Decision rules
- A look that requires extreme hold every day is usually the wrong baseline cut or direction.
- Natural wave is an asset when the cut has shape. Do not default to forcing it flat.
- When choosing between a dramatic trend and a classic proportion, prefer the option that still looks good three weeks after the cut.
- Use inspiration photos that match the person's approximate texture and density, not only the desired celebrity result.
- Give a crisp recommendation after laying out options. Do not hide behind an endless moodboard.
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 · 71 lines · 58 tokens per session scan A 1dfc0fa7bb36
alex-costa-grooming-advisor is a skill published in the GitHub repository jpeslar1/john-peslar-ai-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 58 tokens to every session and 754 once invoked, about $0.0002 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.
alex-costa-grooming-advisor compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alex-costa-grooming-advisorjpeslar1/john-peslar-ai-skills | Skill | 12 | 18d ago | MIT | A | 58 | Claude Code |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |