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-onboardinggit 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-onboarding)<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-onboarding"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-onboarding/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-onboarding"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-onboarding.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 | $0.00111 | $0.00936 |
| Opus 5 | $0.00056 | $0.00468 |
| Sonnet 5 | $0.00022 | $0.00187 |
| Haiku 4.5 | $0.00011 | $0.00094 |
Grade A, and why
vertical-onboarding 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertical onboarding — switch them in, to first value, fast
The incumbent's moat is switching cost. Our wedge is dissolving it. Onboarding is where that promise is kept or broken. Design onboarding as a funnel with one activation milestone, import-first.
1. Import-first, not blank-slate
The default first-run path is "bring your data from {incumbent}", powered by
migration-import-engineer's import contract — not an empty dashboard the user must fill
by hand. A new user should see their own customers/jobs/menu/listings within minutes.
- Offer the import on screen one, with the named incumbent ("Import from ServiceTitan").
- Run it as a dry-run preview the user approves (the import contract's operator step).
- Provide a sample-data fallback ("Explore with example data") for users who can't export yet — never a dead empty state.
2. One activation milestone (define it per product)
Pick the single action that means "this user got value" — the north-star of onboarding. Everything in first-run drives toward it. Examples:
| product | activation milestone |
|---|---|
| quoting (home services) | sent first priced quote |
| online-ordering (restaurants) | published menu + took first test order |
| class-booking (fitness) | imported members + first class booked |
| inventory (retail) | synced catalog + first reorder rule set |
| transaction-coordination (real estate) | first transaction checklist created |
| sponsorship-crm (creator) | first sponsor + deal stage |
Measure time-to-first-value (TTFV); target minutes, not days. State the target in the architecture doc.
3. The onboarding funnel (spec these steps)
1. Identify incumbent → 2. Import (dry-run → approve) → 3. Verify own data
→ 4. Complete the one setup the product needs → 5. Activation milestone → 6. Invite team
Each step: a clear single CTA, skippable where safe, resumable, and with progress shown. Defer everything not on the path to the activation milestone.
4. Reduce setup to the minimum
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 · 90 lines · 111 tokens per session scan A 5bb84e3cccea
vertical-onboarding is a skill published in the GitHub repository avelikiy/great_cto (93 stars, last pushed today), licensed MIT. It adds 111 tokens to every session and 936 once invoked, about $0.0006 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
temporal
Help developers use Temporal for durable execution workflows. Covers CLI commands, SDK patterns (Go, TypeScript, Python, Java), workflow orchestration, and architectural decisions.
nazgul:heartbeat
Run one Nazgul automation-heartbeat tick — triages the work inbox and auto-starts the next objective if idle. Opt-in and default-off; fired by an optional Claude Code native scheduled agent (routine) or run by hand. Use when asked to "run a heartbeat tick", "check the inbox", or to test/debug the heartbeat.
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.
recipe-front-review
Reviews completed frontend implementation for governing-source compliance, scope economy, repository quality, and security, then applies user-approved React corrections.