The Agent Skills Directory

[SAFE]: The skill performs local file system analysis of its own configuration directories (agents, skills, rules) to estimate token usage. No sensitive files or directories outside of the agent's workspace are accessed.
[SAFE]: No remote downloads, external dependencies, or network communications are present in the skill definition.
[SAFE]: The skill uses static analysis and heuristics (e.g., word counts and line counts) to provide recommendations for context management, which is a standard utility for LLM-based systems.

context-budget