team-researchlisted

# Team Research — Answer the Questions Run the RESEARCH phase only, then stop. The researcher and file-finder read `questions.md` (and optionally `repos.md`) — never the user's original task description. ## Input `$ARGUMENTS` is the artifact directory: `docs/plans/<id>/`. If empty, the discovery block below resolves it. The dispatched agents receive `$ARGUMENTS/questions.md` and (when it exists) `$ARGUMENTS/repos.md`. They do **not** read `task.md`. Resolve the artifact directory by running this self-contained block (one bash call — agent threads reset cwd between calls): ```sh # Three-tier artifact-directory discovery (archetype A). # ID_RE + PHASE_FILES canonical from hooks/session-start-recover.mjs. # PHASE_FILES recency mirrors findActiveTopic() in session-start-recover.mjs. # NOTE: this block is duplicated across 8 skills by design (see docs/architecture.md); future: shared discover-topic.sh. ID_RE='^([A-Za-z][A-Za-z0-9_]*-[0-9]+|[0-9]{4}-[0-9]{2}-[0-9]{2})-[a-z0-9][a-z0-9-]*$' PHASE_FILES="task questions research design structure plan" PRED="questions.md" # predecessor artifact this skill consumes # Tier 1 — explicit: $ARGUMENTS names an existing dir → use verbatim. if [ -n "$ARGUMENTS" ] && [ -d "$ARGUMENTS" ]; then echo "$ARGUMENTS"; exit 0 fi # Tier 2 — discover: newest ID_RE dir under docs/plans/ that holds PRED. best=""; best_mtime=-1 # Assumes cwd is the repo/worktree root (where docs/plans/ lives). for dir in docs/plans/*/; do name="$(basenam