The Agent Skills Directory

[PROMPT_INJECTION]: The skill defines a cost-optimization strategy that involves delegating tasks to different agent roles and tiers (e.g., executor, architect, explore) based on task complexity.
Ingestion points: The task parameter within the delegate() function calls (referenced in SKILL.md) serves as the entry point for user-provided instructions.
Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the delegated tasks.
Capability inventory: The skill utilizes the delegate platform tool to spawn secondary agents and uses state_write / state_clear for session management.
Sanitization: No sanitization or validation of the task content is performed before it is passed to the delegation tool.
[DATA_EXFILTRATION]: The skill interacts with a configuration file located at ~/.codex/.omx-config.json to determine its operational status. This access is limited to the skill's own configuration parameters and does not involve the exfiltration of sensitive user data.

ecomode