cmp-inspect

cmp-inspect is a skill for Claude Code, Codex from kvdm-co-pilot/create-cmp. It costs 356 tokens per session (4,491 once invoked), scanned B, original, MIT.

A structured inspection tool for a running Kotlin and Compose Multiplatform interface. It returns the screen hierarchy, positions, sizes, and resolved design tokens as JSON rather than an image.

In plain words
What is it for?
Use it to inspect a live Compose screen, check its design tokens, investigate incorrect padding, or find differences in the interface structure.
Why use it?
Text-based inspection can show the actual spacing, sizes, and theme values, making layout mistakes and differences from the design system easier to locate.

Skill for Claude CodeCodex

Part of the create-cmp plugin — 15 skills, 2 agents, 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-inspect
Any agent
npx skills add kvdm-co-pilot/create-cmp --skill cmp-inspect
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 15 skills, 2 agents, 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-inspect

README.md
[![agentmods](https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/cmp-inspect.svg)](https://agentmods.dev/skills/kvdm-co-pilot/create-cmp/cmp-inspect)
Your own site
<a href="https://agentmods.dev/skills/kvdm-co-pilot/create-cmp/cmp-inspect"><img src="https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/cmp-inspect.svg" alt="Measured on agentmods" height="20"></a>
Per session 356 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,491 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 $0.00356 $0.04491
Opus 5 $0.00178 $0.02246
Sonnet 5 $0.00071 $0.00898
Haiku 4.5 $0.00036 $0.00449

Measured 5d ago against content hash 3abc0932fd25, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

cmp-inspect 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 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.

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-inspect/SKILL.md · 265 lines

How it starts

The opening of the file, as written. The whole thing — 265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cmp-inspect — read a live Compose UI as structured design data

Your job: answer "what did this Compose screen actually render, and does it match the design system?" by inspecting structured JSON — hierarchy + geometry + resolved design tokens — never a screenshot. Screenshots burn tokens, degrade to pixel-guessing for colours/spacing, and can't read theme tokens at all. This skill drives the cmp-inspector MCP over a fixed JSON tree contract.

Before any inspector call: confirm the capability (fail loud)

The cmp-inspector MCP tools are a capability, not a given. Before your first call, confirm they resolve (ToolSearch for "cmp-inspector"). If no tools match, STOP — do not fall back to screenshots, raw adb, or manual Gradle 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 be used — and the report must name what is lost: structured trees and change proofs replaced by pixels.

No-pixels rule. Do not screenshot the app to reason about layout, colour, or spacing. Render the semantics tree and assert on it. The tree carries the resolved design token — strictly better than sampling an image, and 100% structured.

Two loops — pick the right tier first

Tier 0 (headless) — render → dump → inspect. Fast (seconds, incl. compile), no device. Use for previews and layout/token assertions on the app's real screens:

  1. Render with the app's own generated harness — every create-cmp app scaffolded with the inspector feature ships inspector/PreviewRegistry.kt (the @Preview analog: shell, one entry per tab, detail) and a :composeApp:renderScreens Gradle task:

Read the full file on GitHub · 265 lines

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. 5d ago First seen · 265 lines · 356 tokens per session scan B 3abc0932fd25

Subscribe to this mod's changes

cmp-inspect is a skill published in the GitHub repository kvdm-co-pilot/create-cmp (0 stars, last pushed today), licensed MIT. It adds 356 tokens to every session and 4,491 once invoked, about $0.0018 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

liquid-glass

Apple Liquid Glass design patterns for SwiftUI iOS 26 - glass effects, morphing, containers, interactive glass, tinting, accessibility, and cross-platform glass design.

TalissonVitorino/kmp-ios-skills · 40 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

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

offline-first

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

TalissonVitorino/kmp-ios-skills · 26 tokens