buildlisted

# Build Implement in thin vertical slices, test-first, committing atomically, and do not declare done until four gates return clean. Migrated from `.claude/commands/build.md` under ADR-064, which makes skills the single user-invocable surface. ## Triggers `build this`, `implement this slice`, `write the code for this task`, `start building` ## Arguments ultrathink Build: $ARGUMENTS If `$ARGUMENTS` is empty, check for recent plan output in the conversation. If none is found, ask what to build rather than inferring it. ## Cross-Harness Hook Routing If the task touches Claude Code or GitHub Copilot CLI hook configuration, payloads, decisions, matchers, exit codes, timeouts, generated shims, or event translation: 1. Invoke `Skill(skill="agent-harness-reference")` before design or code. 2. Execute the change through `Skill(skill="ai-agents-portability-campaign")`. 3. Use `Skill(skill="ai-agents-generation-and-release")` for generated mirrors. 4. Do not repeat vendor research unless the pinned source ledger is stale or the task explicitly requires a contract refresh. ## Process ### Phase 1: Assess complexity `Task(subagent_type="analyst")`: Read the engineering complexity tiers reference in the `analyze` skill, resolved through `${COPILOT_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-.claude}}/skills/analyze/references/engineering-complexity-tiers.md`, and the task description. Classify as Tier 1-5. Return tier, rationale, and recommended oversight level. Calibrate the imp