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/kvdm-co-pilot/create-cmp/add-screennpx skills add kvdm-co-pilot/create-cmp --skill add-screengit clone --depth 1 https://github.com/kvdm-co-pilot/create-cmpWrote 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/kvdm-co-pilot/create-cmp/add-screen)<a href="https://agentmods.dev/skills/kvdm-co-pilot/create-cmp/add-screen"><img src="https://agentmods.dev/badge/skills/kvdm-co-pilot/create-cmp/add-screen.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 5.1 | $0.00182 | $0.01832 |
| Opus 5 | $0.00091 | $0.00916 |
| Sonnet 5 | $0.00036 | $0.00366 |
| Haiku 4.5 | $0.00018 | $0.00183 |
Grade A, and why
add-screen 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
add-screen — stamp a presentation slice over an existing entity
Deterministic-stamp, gate-proven. The script (
qa/scaffold-feature.mjs --preset screen) does the mechanical work — copy thehomeexemplar's presentation files, whole-word identifier rename, DI injection for the ViewModel only, nav route + import. You (the AI) only refine spec wording and adapt the screen to the entity's real shape. You are not done untilnode qa/verify.mjsPASSes and the receipt is committed — see this project'sCLAUDE.md.
This is the screen subset of add-feature — same stamper, same rename mechanic, filtered to
the 6 presentation+tests+spec files, composed on top of an entity that already exists (via
add-repository or a prior add-feature run). If the entity doesn't exist yet, this will refuse
to stamp anything — see step 2.
Name the lane first, out loud. Before any tool runs, tell the human in a sentence which
lane this request takes (CLAUDE.md §"After genesis"): a screen carrying decisions worth
recording or blast into signed artifacts goes through a feature brief
(docs/features/<name>.md, signed before code); an ordinary screen is direct lane — say
so, then continue here. Never route silently.
Why a stamper and not hand-written files
Every hand-written file is a drift chance in this project's architecture. qa/scaffold-feature.mjs --preset screen produces a conforming skeleton by construction: a Screen composable with a
testTagged root, a ViewModel (+ test), a Compose UI test, a golden-tree test, and a seven-clause
spec — wired into Koin and the nav graph. Your job is to make it behave like the real screen,
not to make it structurally correct.
The flow
1. Name the feature and confirm the entity
Ask the human for the feature/screen name (PascalCase, plural-ish noun — e.g. Tags,
Bookmarks) and the entity it's backed by (e.g. Tag, Bookmark). If they don't give an
entity, the script defaults it by stripping a trailing s/ies from the feature name — naive
de-pluralization is unreliable for irregular nouns, so always show the proposed entity and let
the human confirm or override it before proceeding (--entity <EntityName>).
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 · 143 lines · 182 tokens per session scan A 7e7a40c9662e
add-screen is a skill published in the GitHub repository kvdm-co-pilot/create-cmp (0 stars, last pushed today), licensed MIT. It adds 182 tokens to every session and 1,832 once invoked, about $0.0009 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 2026-08-31.
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…
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.
liquid-glass
Apple Liquid Glass design patterns for SwiftUI iOS 26 - glass effects, morphing, containers, interactive glass, tinting, accessibility, and cross-platform glass design.
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…
offline-first
Offline-first architecture patterns - NetworkBoundResource, sync strategies, conflict resolution, cache invalidation, and connectivity monitoring.
app-intents
Expose a fintech iOS app's actions and data to Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence with the App Intents framework — AppIntent.perform + IntentResult, @Parameter (options/defaults/dependencies), AppEntity + EntityQuery/EntityStringQuery, AppShortcutsProvider phrases…