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 TalissonVitorino/kmp-ios-skills --skill metrickitgit clone --depth 1 https://github.com/TalissonVitorino/kmp-ios-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/talissonvitorino/kmp-ios-skills/metrickit)<a href="https://agentmods.dev/skills/talissonvitorino/kmp-ios-skills/metrickit"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/metrickit/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/talissonvitorino/kmp-ios-skills/metrickit"><img src="https://agentmods.dev/badge/skills/talissonvitorino/kmp-ios-skills/metrickit.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 | $0.00197 | $0.03777 |
| Opus 5 | $0.00098 | $0.01888 |
| Sonnet 5 | $0.00039 | $0.00755 |
| Haiku 4.5 | $0.00020 | $0.00378 |
Grade A, and why
metrickit 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MetricKit (iOS production telemetry)
Field-collected power/performance metrics and crash/hang/exception diagnostics, aggregated on-device by the system and delivered to your app — no third-party SDK, no per-event network cost. Grounded in Apple's MetricKit framework.
- On-device & privacy-preserving: the OS aggregates over a 24h window and hands you a payload; nothing leaves the device until you upload it. No PII, no user identifiers — safe for a fintech privacy posture. Still declare any upload/collection in the privacy manifest (see
app-store-review). - Delivery cadence: subscriber callbacks fire at most once per day, on a background queue, and only when the app has been foregrounded since the last delivery. Diagnostics can also arrive right after the next launch following a crash/hang.
- Two APIs: the stable delegate-based
MXMetricManager(iOS 13+, crashes/diagnostics iOS 14+) — the default for the iOS 26 era — and the new asyncMetricManager(iOS 27, WWDC26) covered inreferences/new-metricmanager.md. - Not a profiler. MetricKit tells you what regressed in the field, aggregated; to root-cause locally with call trees and allocations use
debugging-instruments.
Contents
- Subscribe
- MXMetricPayload — the metrics
- Custom metrics with mxSignpost
- MXDiagnosticPayload — crashes/hangs/exceptions
- Extended launch diagnostics
- Durable export & upload
- Testing / simulating payloads
- KMP boundary
- New async MetricManager (iOS 27)
- Correctness checklist
- References:
references/payload-fields.md,references/new-metricmanager.md
Subscribe
Register one long-lived subscriber at launch — a payload delivered before you
subscribe is lost. A singleton owned by the app delegate / App is the right scope.
import MetricKit
final class TelemetrySubscriber: NSObject, MXMetricManagerSubscriber {
static let shared = TelemetrySubscriber()
func start() { MXMetricManager.shared.add(self) } // idempotent-safe to guard yourself
func stop() { MXMetricManager.shared.remove(self) }
// Called on a BACKGROUND queue, ~once/day. Both methods are optional.
func didReceive(_ payloads: [MXMetricPayload]) {
for payload in payloads { PayloadStore.persist(payload.jsonRepresentation()) }
}
func didReceive(_ payloads: [MXDiagnosticPayload]) { // iOS 14+
for payload in payloads { PayloadStore.persist(payload.jsonRepresentation()) }
}
}
What ships with it
2 files 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.
- 9d ago First seen · 231 lines · 197 tokens per session scan A fde6e3e46f81
metrickit is a skill published in the GitHub repository TalissonVitorino/kmp-ios-skills (12 stars, last pushed 18d ago), licensed MIT. It adds 197 tokens to every session and 3,777 once invoked, about $0.0010 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
compose-multiplatform
Use when building one shared Compose UI in Kotlin across Android, iOS, and desktop — commonMain @Composables, expect/actual, source-set placement, native interop, multiplatform ViewModel/navigation/Koin. NOT a single-platform native build (that is kotlin-android / swift-ios), and NOT Dart/Flutter cross-platform UI…
cmp-new
Scaffold a new MOBILE app — Android + iOS from one Kotlin/Compose Multiplatform codebase — from a bare "create a mobile app" to a green, verified build. Guardrails first: if the user already chose a different framework (React Native, Expo, Flutter, SwiftUI, native), do NOT redirect them here; if they only asked a…
cmp-firebase-connect
Wire a freshly scaffolded CMP/KMP app to its OWN real Firebase project — the #1 post-scaffold manual step. Use this when the user wants to connect their app to Firebase, or asks "connect my app to firebase", "set up google-services.json", "wire firebase", "create a firebase project for this app", "replace the…
add-feature
Add a new conforming vertical-slice feature (Screen + ViewModel + UseCase + Repository + spec + tests + golden tree + nav route + DI wiring) to this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature (qa/approvals.json's exemplarFeature — home by default). Use this when…
cmp-audit
Adversarial audit of one subsystem of a Kotlin/Compose Multiplatform app against its spec AND against platform semantics — the class of defect desktop-tier tests cannot see (alarms, notifications, PendingIntents, reboot, process death, DST). Use this when the user says "audit the notifications", "double check X for…
add-screen
Add a presentation-only slice — Screen + ViewModel + tests + golden tree + spec + nav route — for an EXISTING entity/repository in this Compose Multiplatform app, cloned deterministically from the project's configured exemplar feature's presentation layer (qa/approvals.json's exemplarFeature — home by default).…