The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute several shell-based operations to manage project state and gather context. This includes running a local Node.js script located at .claude/scripts/set-active-plan.cjs to track active implementation plans and using the GitHub CLI (gh) to read pull requests, issues, and action logs.
[EXTERNAL_DOWNLOADS]: The agent is authorized to use the repomix utility with the --remote flag. This tool downloads and aggregates the content of external GitHub repositories into a single file for the agent to analyze, which involves fetching data from remote servers.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection (Category 8) because it processes untrusted data from external sources.
Ingestion points: Technical context is ingested from remote GitHub repositories (via repomix), as well as pull request comments, issue descriptions, and discussion threads (via gh).
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing these external data streams.
Capability inventory: The agent possesses significant capabilities, including the ability to execute shell commands, manage project tasks via TaskCreate/TaskUpdate, and perform file system writes within the current working directory.
Sanitization: The skill does not describe any sanitization or filtering logic for content retrieved from external GitHub resources before it is interpreted by the agent.

planning