The Agent Skills Directory

[PROMPT_INJECTION]: The skill employs strong imperative framing, such as 'Sovereign Directive' and 'Absolute zero-tolerance,' to override the agent's default behavior and enforce specific stylistic and technical constraints.
[COMMAND_EXECUTION]: Rule R-35 requires the agent to 'Build and execute the code before declaring completion.' This instruction directs the agent to run arbitrary code within the project environment for verification purposes. Additionally, the included 'check-anti-slop.js' script recursively reads and modifies project files to remove specified comment patterns.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and audit external code and documentation. This creates an attack surface where malicious instructions embedded in the audited files could potentially influence the agent's behavior during the audit process.

anti-slop