The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard development commands for validation, such as npm test, npx tsc, and npm run lint. It also suggests the use of platform-specific CLI tools like ask-gemini and codex-cli for multi-agent coordination. These commands are used for their intended purpose within a software development context.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it reads and modifies external source code which could contain instructions designed to influence the agent.
Ingestion points: The skill reads source code using Read, Grep, and Glob tools.
Boundary markers: Absent. There are no specific instructions to use delimiters or ignore instructions embedded in the code being refactored.
Capability inventory: The skill allows for file modification via Write and Edit tools and provides access to shell command execution for testing.
Sanitization: Absent. The skill does not define methods for sanitizing the input code to prevent potential exploitation of the agent's instructions.

code-refactoring