The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard npx codeceptjs CLI commands, including check, list, and dry-run. These commands are used to validate the environment and enumerate project capabilities without executing the full test suite.
[INDIRECT_PROMPT_INJECTION]: The skill involves reading and reporting on untrusted project data, such as configuration files and test definitions. This is a necessary surface for its intended discovery purpose.
Ingestion points: Reads local configuration files (codecept.conf.js/ts) and test files via the dry-run command.
Boundary markers: Not explicitly implemented in the reporting instructions.
Capability inventory: Invokes the npx codeceptjs binary to perform diagnostic tasks.
Sanitization: The skill utilizes official framework tooling to parse project data, reducing the risk of manual misinterpretation.

codeceptjs-fundamentals