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-home-servicesgit 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-home-services)<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-home-services"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-home-services/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-home-services"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-home-services.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 | $0.00132 | $0.02326 |
| Opus 5 | $0.00066 | $0.01163 |
| Sonnet 5 | $0.00026 | $0.00465 |
| Haiku 4.5 | $0.00013 | $0.00233 |
Grade A, and why
vertical-home-services 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 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.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Home & field services — spec it like a trades shop runs
HVAC, plumbing, cleaning, landscaping. A crew of techs in trucks, jobs on site, money quoted at the kitchen table. A builder who models this as "appointments + invoices" ships something no contractor will use. This skill is the domain briefing so the spec is right before code starts.
1. Domain vocabulary (know these or look naive)
- Price book — the master catalog of priced tasks ("replace 40-gal water heater = $1,850"). Pricing is looked up, not computed hourly.
- Flat-rate vs T&M — flat-rate (one price from the price book, parts + labor bundled) is the norm in the trades. Time & materials (T&M, billed by the hour + parts) is the exception, used for diagnostics or open-ended jobs. Build for flat-rate first.
- Dispatch board — the live grid of techs × time slots the office uses to assign and re-shuffle jobs through the day.
- Truck roll — sending a tech to a site. Every truck roll has a real cost; minimizing wasted rolls is the whole game.
- First-time fix rate — % of jobs completed on the first visit. The north-star ops metric. Low fix rate = repeat rolls = lost margin.
- Callback — a return visit because the first fix failed. Tracked and hated; ties to warranty.
- Membership / service agreement — recurring plan (e.g. 2 tune-ups/yr for $19/mo) that creates predictable revenue and priority booking. A core business model, not a loyalty gimmick.
- Good-better-best — the quote presents 3 priced options (e.g. patch / replace / replace-with-upgrade). Standard sales technique; lifts ticket.
- Dispatch fee / trip charge — flat fee just to show up, often waived if the job is booked.
- After-hours / emergency rate — premium pricing for nights, weekends, holidays. Same price book, different multiplier.
- GPS / route — tech locations and optimized drive order; drives the "tech is 12 min away" customer text.
- Parts markup — parts billed above cost (often 2–3×); a margin lever, must be representable per line.
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 · 162 lines · 132 tokens per session scan A 23e8a2431755
vertical-home-services is a skill published in the GitHub repository avelikiy/great_cto (92 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 2,326 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.