The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses bun to execute various shell-based tasks, including bunx tsc for project scanning, bun run typecheck for validation, and bun test for regression testing.
[COMMAND_EXECUTION]: Orchestrates file system modifications through subagents using rm for file deletion and git for committing changes.
[EXTERNAL_DOWNLOADS]: Triggers the download and execution of the TypeScript compiler package via bunx.
[PROMPT_INJECTION]: The skill scans local source code, which acts as a surface for indirect prompt injection. Ingestion points: Files located in the src/ directory. Boundary markers: None explicitly defined in the prompts passed to subagents. Capability inventory: File system write/delete access, shell command execution, and Git repository management. Sanitization: The skill mitigates risks by requiring verification via LSP (LspFindReferences) and compiler-level checks (tsc --noUnusedLocals) before any code is modified or removed, ensuring that only machine-verified dead code is targeted.

remove-deadcode