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-fintech-mobilegit 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-fintech-mobile)<a href="https://agentmods.dev/skills/avelikiy/great_cto/vertical-fintech-mobile"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-fintech-mobile/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-fintech-mobile"><img src="https://agentmods.dev/badge/skills/avelikiy/great_cto/vertical-fintech-mobile.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 133 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00119 | $0.01988 |
| Opus 5 | $0.00060 | $0.00994 |
| Sonnet 5 | $0.00024 | $0.00398 |
| Haiku 4.5 | $0.00012 | $0.00199 |
Grade A, and why
vertical-fintech-mobile 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Money on a phone — spec it like the network will fail mid-transfer
A field app that loses a photo is annoying. A money app that loses — or duplicates — a transfer is a loss, a support case, and sometimes a regulator. Everything in the generic mobile contract still applies (offline queue, idempotency, permissions); this pack is the part that is different because it is money, and it is the part community skill sets do not carry, because it is domain knowledge rather than framework knowledge.
The through-line: the phone is not the ledger. It is a client with an opinion, and every screen must be honest about how strong that opinion is.
1. A balance has three states, never two
confirmed · pending · unknown. A number rendered without which of the three
it is, is a lie the user will act on.
- confirmed — the server said so, and the app has heard from the server recently enough to say when.
- pending — the app has applied its own optimistic change on top. It is a display, not a fact, and it is labelled.
- unknown — the app has not reached the server. This is NOT the last confirmed number rendered as though it were current. A stale balance shown as live is the defect this whole pack exists to prevent.
Every balance carries as of when. "£1,240.55" is not an answer; "£1,240.55, as of 14:02" is.
2. The idempotency key must outlive the process
The generic rule is "client-generated id so a re-sync never duplicates". For money that is not enough, because the process dies.
- Mint the key before the intent leaves the screen, and persist it with the intent in the same durable write. A key held in memory is a key that a crash turns into a second payment.
- The key belongs to the user's intent, not to the attempt. Ten retries of one "send £50" share one key. A second tap of the button is a new intent — or it is a double-send, and the UI decides which by disabling or by asking.
- The server contract must state how long it honours a key. An idempotency window shorter than the app's retry backoff is the same as no idempotency.
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 · 166 lines · 119 tokens per session scan A 89f8db7e645a
vertical-fintech-mobile is a skill published in the GitHub repository avelikiy/great_cto (92 stars, last pushed yesterday), licensed MIT. It adds 119 tokens to every session and 1,988 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
validate-mobile
Run a Maestro flow on an explicitly selected iOS or Android device and report behavioral evidence.
fec-pwa-implementation
A guide for adding Progressive Web App features to a website. A Progressive Web App, or PWA, is a website that can be installed like an app and can offer limited offline use through a web app manifest and a service worker.
swiftui-expert
This skill should be used when the user is building, reviewing, or debugging SwiftUI views and apps. Detects iOS and Swift version from the project. Covers creating views, state management with @Observable, NavigationStack routing, animations, accessibility, performance optimization, Liquid Glass adoption, design…
swiftui-design-consultation
Apple-canon design system for SwiftUI projects: produces DESIGN.md + a Swift Package starter (semantic colors, SF Pro, Liquid Glass, motion, accessibility). Use when starting or refreshing a SwiftUI design system.
ios-native-review
After a PRD/spec/plan for an iOS app, before implementation: validate the artifact against Apple HIG (iOS) via WebFetch citations. Asks "is this iOS-native?" — complements pitfall-verification and quality-review.
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.