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 avelikiy/great_cto --skill vertical-fitnessgit clone --depth 1 https://github.com/avelikiy/great_ctoWrote 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/avelikiy/great_cto/vertical-fitness)<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-fitness"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-fitness/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/avelikiy/great_cto/vertical-fitness"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-fitness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00148 | $0.02838 |
| Opus 5 | $0.00074 | $0.01419 |
| Sonnet 5 | $0.00030 | $0.00568 |
| Haiku 4.5 | $0.00015 | $0.00284 |
Grade A, and why
vertical-fitness 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fitness & wellness — spec it like a studio bills and books
Boutique studios, gyms, coaches, on-demand brands. Members on recurring plans, classes with finite capacity, retention won or lost on attendance. A builder who models this as "events + tickets" ships something no studio owner will run their business on — because the hard parts are billing and waitlists, not the calendar. This skill is the domain briefing so the spec is right before code starts.
1. Domain vocabulary (know these or look naive)
- Class pack vs unlimited membership vs drop-in — three distinct products. A pack is N prepaid classes that decrement (10-class pack); an unlimited membership is a recurring plan (often monthly auto-renew) with no per-class deduction; a drop-in is a single paid visit. The schema must hold all three, not collapse them into "credits".
- Recurring billing / auto-renew — memberships rebill on a cycle (monthly is the norm) until cancelled. This is the revenue engine and the hardest thing to get right (see §2).
- Waitlist — a full class has an ordered queue; when a spot opens (someone late-cancels), the system auto-promotes the next person and notifies them. Core, not optional.
- Late-cancel / no-show fee — cancelling inside the policy window (e.g. <12h) or not showing forfeits the class (pack decrements) or charges a fee. The policy is the booking discipline.
- Class capacity — every class has a hard cap (bikes, mats, reformers). Booking beyond cap goes to the waitlist, never overbooks.
- Recurring class schedule — classes are templates ("Mon/Wed/Fri 6am Spin") that generate dated instances, with per-instance overrides (holiday cancel, sub instructor). Not a list of one-off events.
- Check-in — marking a member present at class; drives attendance history, which drives churn signals and pack decrement.
- Freeze / hold — a member pauses a membership (travel, injury) without cancelling; billing suspends, the plan resumes later. Expected feature.
- MRR / churn rate / LTV — monthly recurring revenue, the % of members who cancel per month, and lifetime value. The owner's scoreboard.
- Punch card — a physical-metaphor pack (10 punches); same model as a class pack with a remaining balance.
- Family / household account — one billing account, multiple members (parent + kids, couples); shared or separate balances.
- Mindbody discovery marketplace — Mindbody's consumer app where users find and book studios. Listing there is a customer-acquisition channel, not just software — see §2 and §5.
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 · 188 lines · 148 tokens per session scan A 6ffbcce59f21
vertical-fitness is a skill published in the GitHub repository avelikiy/great_cto (93 stars, last pushed yesterday), licensed MIT. It adds 148 tokens to every session and 2,838 once invoked, about $0.0007 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
spec-drift
Standalone plan-vs-code audit on any branch: runs /ship Step 8's plan-completion section from disk (hash-pinned) against an explicit plan and base. Report, JSON, exit code. Never edits code.
third-lens-review
After Claude self-pitfall + Codex on a ship-worthy/architecture/RT/security/contract change: run a third external model house (distant training distribution → different blind spots) on the patched artifact, then adversarial synthesis.
quality-review
After a PRD, spec, or plan, before implementation: hunt perceived-quality pitfalls (silent failures, missing loading/empty states, error recovery, state drift) that make a product feel cheap. Complements pitfall-verification.
boundaries
Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
triage
Triage review findings interactively — approve, skip, or prioritize each issue. Use after /phx:review to filter findings before fixing.