The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to inspect the repository, including git status, git rev-parse, find, and cat. These commands are used to gather context on branches, project structure, and task files.- [INDIRECT_PROMPT_INJECTION]: The skill consumes data from project configuration files (.wt.toml and local.toml) to determine workflow policies and task execution shapes. While these files are local to the repository, they represent an external input channel that could influence the agent's behavior.
Ingestion points: Configuration files .wt.toml and .wt/config/local.toml are read from the repository root to configure the skill's execution environment.
Boundary markers: The instructions do not define explicit delimiters or security markers when reading these configuration files.
Capability inventory: The skill has the capability to execute repository inspection commands and orchestrate workflows via the wt CLI tool.
Sanitization: No specific sanitization or validation logic is defined for the data extracted from the configuration files before it is used to define task metadata.

ready