The Agent Skills Directory

[SAFE]: The documentation in SKILL.md and references/context-components.md provides architectural guidance on context management. It does not contain any prompt injection attempts or malicious instructions.
[SAFE]: The Python module scripts/context_manager.py provides utility functions for token estimation and context assembly. The code is well-structured and uses standard libraries for legitimate purposes without any dangerous execution patterns or hidden logic.
[SAFE]: The skill promotes security best practices by recommending the use of XML tags and boundary markers to separate different types of context, which helps prevent accidental obedience to embedded instructions.

context-fundamentals