The Agent Skills Directory

[SAFE]: The skill is purely instructional and defines a process for better software engineering practices. It does not contain any malicious patterns, obfuscation, or unauthorized access attempts.
[NO_CODE]: The skill does not include or execute any scripts, binaries, or external packages. All logic is expressed through markdown instructions for the AI agent.
[INDIRECT_PROMPT_INJECTION]: While the skill ingests untrusted data (user task descriptions) and has the capability to write files (saving plans to a plans/ directory), this behavior is the primary intended purpose of the skill and includes structural safeguards such as mandatory human review and explicit approval gates before any execution occurs.

plan-mode