gsd:resume-work

Detect handoff state. Check for .planning/HANDOFF.json via Read tool. If missing, the session has no handoff — announce "No handoff found" and proceed to normal /gsd:progress routing.

Load STATE.md. Read .planning/STATE.md to restore the big-picture project position. If missing, reconstruct from .planning/ROADMAP.md and the latest phase directory's SUMMARY.md files; if reconstruction fails, surface the error and stop.

Read the handoff. Parse .planning/HANDOFF.json. Extract phase, plan, task, status, source, uncommitted_files, decisions, context_notes, next_action. Per HANDOFF schema, all fields are always present (empty arrays / null for unset).

Present project status. Emit a compact status block covering:

• Milestone + percent complete (from STATE.md frontmatter progress.percent).
• Current phase name and number.
• Plan / task position from the handoff.
• Handoff source (manual-pause vs auto-compact) and timestamp.
• Top 3 decisions and any blockers from the handoff.
• Uncommitted files summary.
• The next_action string verbatim — it's the resumption hint.

Route to the next action. Offer 1-3 concrete options based on handoff state. Common patterns:

• If task was mid-execute: offer /gsd:execute-phase with the current phase.
• If phase is at plan boundary: offer /gsd:plan-phase or /gsd:execute-phase for the next phase.
• If there are uncommitted files that look in-progress: call attention to them before offering continuation.

Clean up the handoff (LIFE-01). After routing — once steps 1-5 have completed without error — remove the handoff file:

node "${CLAUDE_PLUGIN_ROOT:-$(ls -d "$HOME/.claude/plugins/cache/gsd-plugin/gsd/"*/ 2>/dev/null|sort -V|tail -1)}/bin/gsd-tools.cjs" checkpoint --clear

If the command is unavailable for any reason, fall back to direct removal:

rm -f .planning/HANDOFF.json

Do not abort the resume if cleanup fails — it's hygiene, not correctness. The next session's SessionStart will overwrite a stale handoff anyway (per D-05 from Phase 4: latest snapshot wins).