cmp-test

cmp-test is a skill for Claude Code, Codex from kvdm-co-pilot/create-cmp. It costs 227 tokens per session (3,189 once invoked), scanned B, original, MIT.

A tool that creates regression tests for a Compose Multiplatform app by reading the app's rendered semantics tree. That tree is structured information about visible text, controls, identifiers, screen state, and element positions.

In plain words
What is it for?
It is for observing screens, deriving test cases, and writing them into the app's existing test harness.
Why use it?
It bases tests on what the running app actually exposes instead of relying on screenshots or unstructured device commands. It also chooses the test format already used by the project, such as Maestro or a legacy Appium setup.

Skill for Claude CodeCodex

Part of the create-cmp plugin — 14 skills, 1 agent, 4 hooks, 1 MCP server shipped together

Install

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.

agentmods
npx agentmods add skills/kvdm-co-pilot/create-cmp/cmp-test
Any agent
npx skills add kvdm-co-pilot/create-cmp --skill cmp-test
Clone the repo
git clone --depth 1 https://github.com/kvdm-co-pilot/create-cmp

Made for: Claude Code, Codex.

Or install create-cmp, the plugin that ships this one along with the rest of its 14 skills, 1 agent, 4 hooks, 1 MCP server.

Wrote 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.

agentmods badge for cmp-test

README.md
[![agentmods](https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/cmp-test.svg)](https://agentmods.dev/skills/kvdm-co-pilot/create-cmp/cmp-test)
Your own site
<a href="https://agentmods.dev/skills/kvdm-co-pilot/create-cmp/cmp-test"><img src="https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/cmp-test.svg" alt="Measured on agentmods" height="20"></a>
Per session 227 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,189 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00227 $0.03189
Opus 5 $0.00113 $0.01595
Sonnet 5 $0.00045 $0.00638
Haiku 4.5 $0.00023 $0.00319

Measured 3d ago against content hash 9c3e8d34798e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cmp-test scanned grade B with 1 finding 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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (example-generated-home.spec.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

1. **Plugin enabled?** Check `enabledPlugins` in `~/.claude/settings.json` (or the project's
skills/cmp-test/SKILL.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cmp-test — generate the regression suite from the rendered tree

Which harness? Look before you write. Current scaffolds ship Maestro flows (qa/e2e/*.yaml# SPEC:-cited, testTag id: selectors; see smoke.yaml for the shape) and NO Appium directories. The Appium mechanics below apply only to legacy pre-Maestro projects that actually contain qa/appium/ or tests/appium/ — check which exists in the target repo first and emit tests for THAT harness. Durable screen behavior belongs in Compose UI Tests (spec-cited) either way; E2E stays a thin smoke layer.

Before anything: confirm the capability (fail loud)

The cmp-inspector MCP tools are a capability, not a given. Before your first inspector call, confirm they resolve (ToolSearch for "cmp-inspector"). If no tools match, STOP — do not fall back to screenshots, raw adb, or uiautomator dumps silently. Diagnose in order and REPORT to the human:

  1. Plugin enabled? Check enabledPlugins in ~/.claude/settings.json (or the project's .claude/settings.json).
  2. Session older than the plugin's enablement? MCP servers attach at session START — a session born without the plugin never gains its tools, and no amount of in-session retrying will surface them. The fix is restarting the session.
  3. Plugin copy stale or server broken? Run cmp-doctor's inspector-MCP check group.

Only after reporting may the documented degraded path (tier-2 uiautomator page-source) be used — and the report must name what is lost: structured semantics trees replaced by pixels and raw XML.

Your job: turn "write tests for my app" into a committed, passing E2E suite — by observing the app, not guessing from source. Every create-cmp app is AI-inspectable: the cmp-inspector MCP reads the running UI as structured JSON (testTags, text, clickable nodes, bounds, navigation state). You read that tree, enumerate what's actually on screen, derive the assertions, and emit tests in the app's shipped harness style. Nothing else in the CMP ecosystem can close this loop.

Read the full file on GitHub · 208 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 3d ago First seen · 208 lines · 227 tokens per session scan B 9c3e8d34798e

Subscribe to this mod's changes

cmp-test is a skill published in the GitHub repository kvdm-co-pilot/create-cmp (0 stars, last pushed 5d ago), licensed MIT. It adds 227 tokens to every session and 3,189 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

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…

ericrisco/rsc-harness · 80 tokens

m3-expressive

Material 3 Expressive design patterns for Jetpack Compose - expressive theming, motion physics, shape morphing, typography emphasis, color emphasis, and all 28 expressive components.

TalissonVitorino/kmp-ios-skills · 41 tokens

android-device-integrity

Android app/device integrity and anti-fraud for a fintech app — the Play Integrity API (com.google.android.play:integrity): Standard requests (StandardIntegrityManager.prepareIntegrityToken → StandardIntegrityTokenProvider.request with a requestHash → StandardIntegrityToken) vs Classic requests…

TalissonVitorino/kmp-ios-skills · 260 tokens

offline-first

Offline-first architecture patterns - NetworkBoundResource, sync strategies, conflict resolution, cache invalidation, and connectivity monitoring.

TalissonVitorino/kmp-ios-skills · 26 tokens

cloudkit

Implement, review, or debug iCloud sync in iOS/macOS apps with CloudKit. Covers CKContainer + private/public/shared CKDatabase, CKRecord / CKRecord.Reference / CKAsset, CKQuery + CKQueryOperation, CKSubscription (query/database/recordZone) with silent push, CKSyncEngine (iOS 17+: state serialization…

TalissonVitorino/kmp-ios-skills · 209 tokens

mobile-session-security

KMP + iOS/Android session hardening for a fintech app — inactivity auto-lock (track last-interaction, idle timeout, biometric/passcode re-auth), biometric re-lock on background/foreground with a grace period, and screen-capture/snapshot protection. Android: WindowManager FLAGSECURE (blocks screenshots + recents…

TalissonVitorino/kmp-ios-skills · 209 tokens