The Agent Skills Directory

[SAFE]: The skill serves as a tool-dispatch guide, organizing development tasks within a 'PACE' framework. It defines a logical workflow for an agent to follow.
[COMMAND_EXECUTION]: Instructions include the use of common CLI tools and packages such as npx ecc-agentshield for security scanning and npx ctx7 for documentation retrieval. These commands are consistent with the skill's stated purpose of development orchestration and do not involve suspicious execution patterns.
[DATA_EXPOSURE]: The skill manages internal project state by writing review findings to .ai_state/reviews/. This behavior is limited to the local environment for maintaining development history and does not involve unauthorized external transmission of data.
[PROMPT_INJECTION]: The instructions focus on tool selection and workflow management. There are no attempts to override agent safety protocols, extract system prompts, or bypass content constraints.

tool-dispatch