karvey-taskslisted

# Karvey Tasks ## Purpose Generate the implementation task plan from the approved architecture. Record it in the team's tracker (Epic > Feature > Tasks with dependencies — `../karvey/rules/management-adapters.md`) or in a PLAN.md checklist. Target size: 10–30 minutes per task (AI timings). ## Execution steps ### Step 1 — Load context Read: - `docs/spec/changes/{change-id}/spec.json` - `docs/spec/changes/{change-id}/requirements.md` - `docs/spec/changes/{change-id}/architecture.md` - `docs/spec/changes/{change-id}/infra.md` (absent when infra was skipped) - `../karvey/rules/management-adapters.md` and `../karvey/rules/clickup-protocol.md` (estimation rules for every tool; the ClickUp adapter) Preconditions (the tasks gate): ```bash S="${CLAUDE_PLUGIN_ROOT}/scripts/karvey-state.py" C="${CLAUDE_PLUGIN_ROOT}/scripts/karvey-config.py" python3 "$S" next "{change-id}" --json # architecture and infra approved or skipped; else relay the blockers and stop python3 "$C" resolve management --change "{change-id}" --json # tool, location, status map; `external` says whether a tracker exists ``` If `resolve` reports the status map missing, apply the missing-map clause of `management-adapters.md` before any status is written; do not restate or improvise it. Then `python3 "$S" advance "{change-id}" tasks`. Determine sequential mode: if `--sequential`, do not use parallelism markers. ### Step 2 — Generate tasks.md draft For each Feature identified in architecture