The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on shell commands using the archlang CLI to perform floor plan manipulations. It provides instructions to use npx -y @chanmeng666/archlang to ensure the tool is available.\n- [EXTERNAL_DOWNLOADS]: The skill utilizes the @chanmeng666/archlang package, which is a resource provided by the skill's author and may be fetched from the NPM registry during execution.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by processing external .arch files.\n
Ingestion points: Content from .arch files is read into the agent's context through commands such as archlang describe and archlang validate (SKILL.md).\n
Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from following instructions potentially embedded in the file data.\n
Capability inventory: The agent has the ability to execute shell commands (via the archlang CLI) and modify the local file system.\n
Sanitization: The skill does not describe any methods for sanitizing the input data from the floor plan files before processing.

archlang-edit-plan