The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands such as find, node, and git to manage persistent state files in the .planning/debug directory and read project configurations. These operations are functional and restricted to the workspace.
[DYNAMIC_EXECUTION]: The skill dynamically constructs prompts for subagents using string interpolation of user input and instruction files, which is a core part of its subagent-based debugging workflow.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data which can influence the agent's behavior.
Ingestion points: User-provided symptoms and reproduction steps via $ARGUMENTS, and any code or log files read from the local workspace during investigation.
Boundary markers: Structural tags like <symptoms> and <agent-instructions> are used in prompt templates to separate instructions from data.
Capability inventory: The skill possesses the ability to execute shell commands, read and write files in the local workspace, and spawn subagents.
Sanitization: No formal sanitization or validation is applied to user-supplied input or workspace file contents before they are interpolated into prompts.

kata-debug