sprint_devlisted

# sprint_dev Own the assigned unit from accepted task through merge. ## Activate from the record The boot sprint directive names every active developer role. Read the scoped task and board: ```sh ./sc mem message check ./sc sprint board --sprint <doc-id> ./sc mem get doc --doc <doc-id> ``` Confirm the unit, scope, dependency, reviewer, branch, and governing spec. The board assigns ownership; the latest scoped task supplies current instructions. Keep one current-state line while active: ```text SPRINT doc=<id> unit=<seq> status=<pending|working|in_review|blocked> ``` Every transition and ruling request goes to the planner as a durable scoped result: ```sh ./sc mem message send <planner> "$(<./sprint-result.md)" \ --kind result --sprint <doc-id> ./sc mem message sent ``` Compose message and task bodies via a file, never inline in a quoted shell string: backticks and `$()` execute before `sc` receives the body. Write the body to `./sprint-result.md`, send its content as one argument, then use `message sent` to read the stored row back and confirm its body. File findings, flags, PRs, and reports within your assigned authority. A question printed only in final output reaches no sprint actor. Message IDs are scoped to their recipient. Treat an ID from another actor's inbox as provenance, never as a fetch instruction; the task row must quote the substance you need. Ask the planner for that substance when it is absent. For DB-assigned document, task, flag, and message