Scan a Kotlin or Compose Multiplatform diff for known footgun shapes and open the matching trap to confirm each hit. Use before committing, when reviewing a Kotlin change, or to audit a codebase.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
scripts/scan.py matches 32 patterns against the lines a change adds. Each pattern is tied to one
trap file in the kotlin-footguns area skills. It finds shapes, not bugs: every hit needs the trap's
judgment before it becomes a finding.
From inside the user's git repository, with this skill's base directory as <skill>:
python3 <skill>/scripts/scan.py # lines added in the working tree and index since HEAD
python3 <skill>/scripts/scan.py --base origin/main # lines added on this branch since it left main
python3 <skill>/scripts/scan.py --all src/ # every line under a path: an audit, and noisier
Pick the scope from the request. Uncommitted work takes the default. A branch or pull request takes
--base with its target branch. "Audit the codebase" takes --all, narrowed to the paths that matter.
For a pre-commit hook or CI step, add --fail to exit 1 on any likely hit.
-> path).likely hit is wrong unless the exception the trap names holds. A look hit is a place the
trap says to inspect before trusting it.Hits of one detector in one file are grouped: triage the group once, then check the listed lines for exceptions.
It needs python3 and git. Without them, read scripts/scan.py: the DETECTORS list gives
each pattern, its message and its trap. Run those patterns with the Grep tool over the changed
files and triage the same way.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Compose screen and interaction traps: navigation, adaptive layout, window insets, pagers, toolbars, sheets, list drag and selection, sliders, text fields, settings UI, one-shot effects. Use when layout, gestures or navigation misbehave.
The English summary is being prepared. Showing the original description.
Compose look-and-feel traps: theme and colour tokens, artwork palettes, gradients and scrims, shimmer, glass and particle effects, animation, image loading, charts and stats displays (percent changes, shares, buckets). Use when a visual bands, pops, freezes or misleads.
The English summary is being prepared. Showing the original description.
Room/SQLite, DataStore and repository traps: migrations, NOT IN with NULLs, LIKE escaping, delete order, local-time bucketing, imports, caching, paging. Use before writing a query or migration, or when data comes back wrong.
The English summary is being prepared. Showing the original description.
Desktop JVM and build traps: JNA natives, bundling, memory, packaging, code signing, R8, deep links, Gradle and CI releases. Use when a desktop build fails packaged, signed, on another OS or arch, or in CI.
The English summary is being prepared. Showing the original description.
Debugging-method traps: run the discriminating experiment first, read build logs bottom-up, treat an empty actual as unwritten, audit shared handles before removing a feature, read commit history critically. Use when a fix is not converging.
The English summary is being prepared. Showing the original description.
Kotlin Multiplatform structure and language traps: module splits, expect/actual, Koin and ViewModel scoping, layers, version catalogs, erased overloads, Char and string-resource formatting limits. Use when shaping modules or DI, when a format specifier renders verbatim, or code misbehaves on one platform.
The English summary is being prepared. Showing the original description.