The Agent Skills Directory

[COMMAND_EXECUTION]: The instructions direct the agent to execute a local JavaScript file (swarm-watch.mjs) located within the plugin's root directory using the node runtime via the Monitor tool.
[INDIRECT_PROMPT_INJECTION]: The skill processes real-time swarm status events that originate from external tool outputs (swarm status), which could potentially contain adversarial instructions.
Ingestion points: Output from the swarm status command processed by swarm-watch.mjs as described in SKILL.md.
Boundary markers: No delimiters or specific warnings are provided to help the agent distinguish between data and instructions.
Capability inventory: The skill has access to execute local scripts and invoke MCP plugin tools (mcp__plugin_ruflo-core_*).
Sanitization: No sanitization, filtering, or validation of the incoming swarm data is documented.

monitor-stream