Borrowing it
Nothing to install: this file belongs to jonapoul/aktual. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/jonapoul/aktual/main/.claude/skills/pr-screenshots/SKILL.mdgit clone --depth 1 https://github.com/jonapoul/aktualWrote 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/jonapoul/aktual/pr-screenshots)<a href="https://agentmods.dev/skills/jonapoul/aktual/pr-screenshots"><img src="https://agentmods.dev/badge/skills/jonapoul/aktual/pr-screenshots/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/jonapoul/aktual/pr-screenshots"><img src="https://agentmods.dev/badge/skills/jonapoul/aktual/pr-screenshots.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00049 | $0.01077 |
| Opus 5.5 | $0.00020 | $0.00431 |
| Sonnet 5.5 | $0.00010 | $0.00215 |
| Haiku 4.5 | $0.00005 | $0.00108 |
Grade A, and why
pr-screenshots 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 — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grab images of changed UI and put them in the PR description. Works with no display, so it suits cloud sessions. It renders composables in a desktop Compose test, not the running app.
1. Pick what to capture
$ARGUMENTSsays what to capture, if given. Otherwise take the composables changed on this branch (git diff origin/main --stat, then look in*/ui/and*/components/modules).- Prefer the scaffold/content composable that takes plain state (e.g.
InfoScaffold(state, onAction)), not theScreenthat needs a VM. Build the state from the file's@Previewfunctions, which are private, so copy their arguments. - Default to dark colors. Add
LightColors(andMidnightColors) only when the change is about color, or when asked. - Keep it small: one or two images per changed screen or state.
2. Write a throwaway test
Create <module>/src/desktopTest/kotlin/<package>/ScreenshotTest.kt in the module that owns the composable, in the same package so internal composables are visible. Every compose module already has aktual-test:compose on its test classpath.
package aktual.about.ui.info
import aktual.core.theme.LightColors
import aktual.test.screenshot
import androidx.compose.ui.test.onNodeWithText
import androidx.compose.ui.test.performClick
import kotlin.test.Test
class ScreenshotTest {
// Full screen, phone size, dark colors
@Test fun info() = screenshot("info") { InfoScaffold(buildState = STATE, onAction = {}) }
// Cropped to the composable's own size, for components and dialogs
@Test
fun dialog() = screenshot("no-update-dialog", fitContent = true) {
NoUpdateFoundDialogContent(onDismiss = {})
}
// Interact before capture
@Test
fun sortSheet() =
screenshot("sort-sheet", colors = LightColors, interact = { onNodeWithText("Sort").performClick() }) {
LicensesScaffold(...)
}
}
screenshot() lives in aktual-test/compose/src/desktopMain/kotlin/aktual/test/Screenshots.kt. Parameters: colors, widthDp/heightDp (default phone, use MY_MONITOR_WIDTH_DP/MY_MONITOR_HEIGHT_DP for desktop layouts), density (default 2), fitContent, interact.
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.
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 · 91 lines · 49 tokens per session scan A 597de6cac385
pr-screenshots is a skill published in the GitHub repository jonapoul/aktual (43 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 1,077 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-11-01.
pr-screenshots compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pr-screenshotsjonapoul/aktual | Skill | 43 | yesterday | Apache-2.0 | A | 49 | Claude Code |
| compose-component-designchrisbanes/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 41 | Claude Code |
| maui-accessibilitydotnet/maui-labs | Skill | 235 | yesterday | MIT | A | 60 | Claude Code, Codex |
| compose-uiMeet-Miyani/compose-skill | Skill | 303 | 14d ago | MIT | A | 148 | Claude Code |
| compose-visuals-footgunsmaxrave-dev/kotlin-footguns | Skill | 2.0k | 8d ago | GPL-3.0 | A | 65 | Claude Code |
| compose-screens-footgunsmaxrave-dev/kotlin-footguns | Skill | 2.0k | 8d ago | GPL-3.0 | A | 57 | Claude Code |
| m3-expressiveTalissonVitorino/kmp-ios-skills | Skill | 16 | 2mo ago | MIT | A | 41 | Claude Code, Codex |