ship-sprintlisted

# Shipyard: Sprint Planning Plan a new sprint by pulling features from the backlog and decomposing into waves. ## Context !`shipyard-context path` !`shipyard-context view config` !`shipyard-context view backlog` !`shipyard-context view sprint` !`shipyard-context view metrics` !`shipyard-context view codebase 30` **Paths.** All Shipyard file ops use the absolute SHIPYARD_DATA prefix from the context block (no `~`, `$HOME`, or shell variables). Shipyard binaries you may invoke from Bash: `shipyard-data archive-sprint <id>`, `shipyard-data init-sprint <id>` (Step 12), `shipyard-data sprint set <key> <value>` and `shipyard-data sprint check` (Step 12). **Never `cd` into the data directory before running `shipyard-data` commands** — they resolve the data directory internally via git and env vars; `cd`-ing into a non-git directory breaks the resolver. Just run the command bare from the project root. **Never use `echo`, `printf`, or shell redirects (`>`) to write state files.** SPRINT.md and PROGRESS.md are created by the `init-sprint` CLI (template-canonical); **SPRINT.md frontmatter is thereafter mutated only via `shipyard-data sprint set`, never a hand Edit** (hand-editing frontmatter is the corruption class that welds keys together). **PROGRESS.md and the pipeline cursors are CLI/render-owned — the model never writes them** (a PreToolUse hook denies such writes). Use the Write tool (auto-approved for SHIPYARD_DATA) for arbitrary *narrative* artifacts (feature files, task fil