What problem does it solve? It turns an OpenSpec change's task list into actual code changes by guiding the AI through selecting the change, reading its context files, and checking off tasks one by one. ## Core Features & Use Cases - Change selection and status tracking: Resolves the target change from user input or context, then reads schema, progress, and task state via openspec status and openspec instructions apply. - Guided task implementation loop: Reads the change's context files (proposal, specs, design, tasks), implements each pending task, and marks it complete in the tasks file. - Guardrails and pause handling: Stops on ambiguity, design issues, scope creep, or errors, and reports structured progress output on completion or pause. - Use Case: After drafting an OpenSpec change for a new feature, ask the AI to apply it; it will work through every task, update the checkboxes, and suggest archiving when done. ## Quick Start Ask the AI to implement the tasks from your OpenSpec change, optionally naming the change, for example by saying apply the add-auth change.
