The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes several bash command snippets designed to verify project architecture. These commands use common utilities such as grep, sed, sort, and uniq to search through the codebase for specific import patterns and class declarations.
[INDIRECT_PROMPT_INJECTION]: The provided diagnostic scripts create a surface for indirect prompt injection by reading and processing local source code files (Kotlin and Gradle files).
Ingestion points: The scripts read from directories defined by variables such as DOMAIN_SRC, DATA_SRC, and APP_SRC, as well as build configuration files in core/service/*/.
Boundary markers: There are no specific delimiters or instructions used to separate the content of the files being read from the agent's instructions.
Capability inventory: The skill uses shell execution to perform text searching and processing on local files.
Sanitization: The results of the grep commands are passed directly to the output without sanitization or validation of the file content.

clean-arch-kmp-readiness