The Agent Skills Directory

[SAFE]: The skill operates exclusively on local project files within the .okr directory. It does not access sensitive system paths, environment variables, or user credentials.
[SAFE]: There are no network operations, external downloads, or remote code execution patterns. All analysis and logging are performed on local data.
[SAFE]: The skill incorporates a safety checkpoint by instructing the agent to ask the user for confirmation before applying any modifications to the project's 'Single Source of Truth' (SOT) files.
[SAFE]: The skill processes project files (objectives, plans, and logs) which are ingestion points for indirect prompt injection. However, the risk is mitigated by the specific task focus and the requirement for user approval for any resulting actions.
Ingestion points: .okr/objective.md, .okr/plan.md, .okr/actions/, and .okr/log/.
Boundary markers: Absent.
Capability inventory: Local file read and write within the project directory.
Sanitization: Absent; the skill relies on user review of proposed changes.

okr-review