The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the bd CLI and git for issue tracking and repository management. These operations, such as bd sync and git worktree management, are essential to the primary function of the workflow.
[PROMPT_INJECTION]: The multi-agent delegation architecture (Prometheus, Atlas, Forager) involves an indirect prompt injection surface as information flows through the task chain.
Ingestion points: Data from hive_plan_write and .hive/ context files are ingested and used to generate prompts for downstream agents.
Boundary markers: The skill does not define specific boundary markers or 'ignore' instructions when interpolating plans into worker prompts.
Capability inventory: The orchestrator has the ability to spawn agents via task() and modify the project state through hive_merge and git push.
Sanitization: No sanitization of ingested plans or context data is mentioned before processing.
[SAFE]: The identified patterns are inherent to the skill's purpose as an orchestration framework. All tools and resource patterns align with the specified vendor (nanomicon) and established developer workflows.

beads-hive-omo-workflow