The Agent Skills Directory

[COMMAND_EXECUTION]: The skill configures and deploys local hooks (run-story-hook.sh, run-story-hook.cmd, and story_codex_hook.py) that are executed during various agent lifecycle events (e.g., project startup, before using tools, and at the end of a session). These scripts are used for environment setup and project context management.
[COMMAND_EXECUTION]: The story_codex_hook.py script uses subprocess.check_output to execute git commands (git rev-parse --show-toplevel, git diff) and cygpath to resolve project paths and identify modified files for content validation. This is a standard practice for project-aware tools.
[DATA_EXFILTRATION]: The skill performs read operations on local project files such as .active-book, _tracking-state.json, and chapter files to maintain a writing context. This data is processed locally within the agent's environment and no evidence of exfiltration to external domains was found.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns, external package installations, or remote script downloads were detected. All executable components are bundled within the skill repository.

story-setup