The Agent Skills Directory

[SAFE]: The skill is purely instructional and focuses on context management protocols for internal project files without performing network operations or command execution.
[PROMPT_INJECTION]: The skill defines a process for reading external files which constitutes an indirect prompt injection surface.
Ingestion points: The skill instructs the agent to read .agent-team/rules/index.md, worker.yaml, task.yaml, and context.md from the local environment.
Boundary markers: No specific delimiters or safety instructions to ignore embedded commands are present in the skill text for the ingested content.
Capability inventory: The skill specifies the capability to read content from the local file system.
Sanitization: No sanitization, validation, or escaping procedures are defined for the data retrieved from the referenced files.

context-cleanup