recipe-fullstack-implement

Required Skills [LOAD BEFORE EXECUTION]

1. [LOAD IF NOT ACTIVE] subagents-orchestration-guide — canonical Fullstack Flow, approvals, and autonomous execution
2. [LOAD IF NOT ACTIVE] documentation-criteria — scale-selected document path
3. [LOAD IF NOT ACTIVE] requirement-convergence — outcome, exclusions, and rough-cost challenge
4. [LOAD IF NOT ACTIVE] llm-friendly-context — cross-agent handoffs and Small task carrier

Every spawn_agent call uses fork_turns="none" and supplies only the exact artifacts needed by that specialist.

Requirements or continuation instruction: $ARGUMENTS

Entry

• New or scope-changing requirements: invoke requirement-analyzer for compact scope/cost evidence; the orchestrator completes Requirement Convergence, determines scale and layer routing, and obtains requirement confirmation.
• Existing PRD, UI Spec, Design Docs, Work Plan, or tasks: resume at the next incomplete Fullstack Flow phase. Restart requirement analysis when the approved outcome, requirement, or exclusion changes.
• Quality failure during an existing implementation: resume its task cycle and Orchestrator Escalation Resolution.

Resolve the entry from supplied artifacts and repository state. Ask only when different interpretations require a user-owned product or approved-design decision.

Flow

Apply the Fullstack Flow exposed by subagents-orchestration-guide with backend, frontend, and shared routing. The orchestrator directly owns artifact/path resolution, execution-plan updates, approval recording, task-set computation, commits, and lightweight checks; invoke the named specialists for analysis, authoring, implementation, review, and quality judgment.

Reuse the active execution plan or register the material remaining phases once. Follow the Fullstack Flow's document approvals. After implementation-scope approval, execute tasks autonomously through its filename routing, Per-Task Change Set, quality gate, commit, and Post-Implementation Review.

Apply a security-reviewer finding only when leaving it unresolved would violate an explicit governing requirement or repository rule, or leave a concrete material security failure in the actual reachable trust model. The violated requirement, rule, or failure defines implementation scope: route the smallest correction that resolves it, treating the reviewer's suggestion as one candidate implementation.