The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run standard development commands such as bun test, bun run lint, and bun run typecheck. These are used for automated verification and QA of the generated plan steps.
[REMOTE_CODE_EXECUTION]: The skill mentions spawning sub-agents and using MCP tools like context7 and general-purpose for codebase analysis and research. These are standard platform tools used for the skill's primary purpose of implementation planning.
[PRIVILEGE_ESCALATION]: No privilege escalation patterns detected. The skill operates within the user's project directory and thoughts/ folder.
[DATA_EXFILTRATION]: No data exfiltration patterns detected. Network operations are limited to standard research tools (sub-agents) and do not target unauthorized external domains.

v-planning