Tracely is a CI/CD system for AI agents that turns failed production traces into replayable regression tests. Development teams use it to detect and group agent failures, run the resulting cases on pull requests, and block changes that reproduce those failures. The catalogue entries provide skills for operating this trace-based testing and observability workflow.
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 agentmods add skills/jwuthri/tracely-ai/compose-multiplatformnpx skills add Jwuthri/Tracely-ai --skill compose-multiplatformgit clone --depth 1 https://github.com/Jwuthri/Tracely-aiWrote 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/jwuthri/tracely-ai/compose-multiplatform)<a href="https://agentmods.dev/skills/jwuthri/tracely-ai/compose-multiplatform"><img src="https://agentmods.dev/badge/skills/jwuthri/tracely-ai/compose-multiplatform.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00040 | $0.03469 |
| Opus 5 | $0.00020 | $0.01734 |
| Sonnet 5 | $0.00008 | $0.00694 |
| Haiku 4.5 | $0.00004 | $0.00347 |
Grade A, and why
compose-multiplatform 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 5d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- compose-multiplatform — 97% identical, 2 lines differ
- compose-multiplatform — 97% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 312 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compose Multiplatform
Compose Multiplatform (CMP) and Kotlin Multiplatform (KMP) patterns for cross-platform UI. Loaded for projects with
org.jetbrains.composeplugin. Foundation:../compose-motion/SKILL.mdfor animation API; this file covers what's specific to writing one Compose codebase for Android + iOS + Desktop + Web.
KMP vs CMP - quick clarification
KMP (Kotlin Multiplatform) is the language and build infrastructure: shared Kotlin code compiled to JVM, Native (iOS, macOS, Linux, Windows), and Wasm. CMP (Compose Multiplatform) is the UI framework on top of KMP, built by JetBrains as a port of Jetpack Compose. You write a single Compose codebase in commonMain that runs on Android, iOS, Desktop (JVM), and Web (Wasm). Platform-specific code lives in androidMain, iosMain, desktopMain, wasmJsMain and is wired in via expect/actual declarations.
Project structure
composeApp/
├── src/
│ ├── commonMain/ ← shared Compose code (most of the app)
│ │ └── kotlin/
│ ├── androidMain/ ← Android-specific (uses Activity, Context)
│ ├── iosMain/ ← iOS-specific (uses UIKit/UIView interop)
│ ├── desktopMain/ ← JVM desktop (uses java.awt/swing if needed)
│ └── wasmJsMain/ ← Wasm web target
├── build.gradle.kts
iosApp/ ← Xcode project consuming the generated framework
androidApp/ ← Android Application module (often merged into composeApp)
The commonMain folder should hold 80-95% of your code in a well-architected CMP project. If iosMain or androidMain start growing past a few hundred lines, you're probably leaking platform concerns into UI logic that could stay shared.
expect/actual pattern
The KMP escape hatch when you genuinely need different implementations per target. Declare the contract once in commonMain, implement it once per target.
// commonMain
expect fun openShareSheet(text: String)
// androidMain
actual fun openShareSheet(text: String) {
val intent = Intent(Intent.ACTION_SEND).apply {
type = "text/plain"
putExtra(Intent.EXTRA_TEXT, text)
}
context.startActivity(Intent.createChooser(intent, null))
}
// iosMain
actual fun openShareSheet(text: String) {
val activityVC = UIActivityViewController(
activityItems = listOf(text),
applicationActivities = null
)
UIApplication.sharedApplication.keyWindow
?.rootViewController
?.presentViewController(activityVC, true, null)
}
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.
- 5d ago First seen · 312 lines · 40 tokens per session scan A f514f00cbe70
compose-multiplatform is a skill published in the GitHub repository Jwuthri/Tracely-ai (1,189 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 3,469 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ci-watchdog
Continuously monitor GitHub PR CI checks and automatically fix failures until all checks pass. USE THIS SKILL when: The user wants to "keep an eye on CI" or "wait for checks to pass" The user mentions monitoring PR status, CI status, or GitHub checks The user asks to watch a PR until it's ready or fix failing checks…
eas-workflows
EAS service (paid). Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.
github-actions
GitHub Actions workflow patterns for React Native iOS simulator and Android emulator cloud builds with downloadable artifacts. Use when setting up CI build pipelines or downloading GitHub Actions artifacts via gh CLI and GitHub API.
flutter-cicd
Set up CI/CD pipelines for Flutter apps. Use when configuring automated testing, build, or deployment workflows with GitHub Actions or Fastlane.
android-tooling
Configure Android static analysis with Detekt, Ktlint, and Android Lint for CI/CD quality gates. Use for Android-specific lint and quality tooling; defer generic Java Checkstyle, SonarQube, and standalone CI configuration.
expo-cicd-workflows
Helps understand and write EAS workflow YAML files for Expo projects. Use this skill when the user asks about CI/CD or workflows in an Expo or EAS context, mentions .eas/workflows/, or wants help with EAS build pipelines or deployment automation.