recipe-implement

## Required Skills [LOAD BEFORE EXECUTION] Before loading required skills, use `wc -c` to size the files and set both `exec_command.max_output_tokens` and the outer `// @exec: {"max_output_tokens": N}` budget to accommodate their contents, including the combined output of batched reads. Split oversized reads upfront; recover any truncated content before proceeding. 1. [LOAD IF NOT ACTIVE] `subagents-orchestration-guide` — agent coordination and workflow routing 2. [LOAD IF NOT ACTIVE] `documentation-criteria` — scale-selected document path 3. [LOAD IF NOT ACTIVE] `requirement-convergence` — outcome, exclusion, and rough-cost convergence before design 4. [LOAD IF NOT ACTIVE] `llm-friendly-context` — cross-agent handoffs and task carrier **Invocation rule**: Start each named agent with `spawn_agent` and `fork_turns="none"`. When invoking the same named agent again within this flow, use `followup_task` on its existing instance with the inputs specified for the current invocation. # Full-Cycle Implementation $ARGUMENTS ## Orchestrator Definition **Core Identity**: Coordinate the lifecycle, complete lightweight workflow operations directly, and invoke named specialists for their domain work. Follow the scale-selected flow and its user approval points from subagents-orchestration-guide. ## Step 1: Requirement Analysis Apply the subagents-orchestration-guide Requirement Evidence Handoff, then invoke requirement-analyzer for compact scope evidence, cost evidence, affected-layer evidence, and decision-changing questions. At the requirements stop, the orchestrator compares the evidence with its retained user record and applies subagents-orchestration-guide `Requirement Convergence`. User selections establish requirements and exclusions; the orchestrator judges readiness, determines Structural Scale and affected layers, and selects the canonical route. Immediately before the stop, read `requirement-convergence`'s `references/scope-confirmation.md` and render that output from the retained user record and analyzer evidence. Render each unanswered product, UX, or operational decision under **User decisions** as an unresolved question followed by its answer-dependent effects. Only an explicit user selection moves it into **Confirmed scope**. Record Structural Scale and workflow routing under **Workflow**. **[STOP — BLOCKING]** Present the Scope Confirmation to the user, then proceed after explicit confirmation. ## Step 2: Canonical Workflow Routing Apply the subagents-orchestration-guide `Basic Flow for Work Planning` using `scale` as the primary route. Use `affectedLayers` only to select the layer-specific additions and agents within that route: | affectedLayers | Layer-specific routing | |---|---| | `["backend"]` only | Backend agents | | `["frontend"]` only | UI Spec when required by the canonical flow, then frontend designer, executor, and quality fixer | | `["backend", "frontend"]` | Fullstack monorepo flow with complete-scope codebase analysis plus layer-specific design and task routing | The scale-selected Large, Medium, or Small flow remains authoritative for document creation, codebase analysis, design verification, planning, and execution. ## Autonomous Execution Mode Enter autonomous execution when the subagents-orchestration-guide `Work Plan Authorization` is satisfied. ### Per-Task Execution Cycle For a fullstack task set, apply `subagents-orchestration-guide`'s `references/monorepo-flow.md` filename routing. For a single-layer task set, use the executor and quality fixer selected by `affectedLayers`. Execute each task through the canonical autonomous task cycle. ### Post-Implementation Review (After All Tasks Complete) Apply subagents-orchestration-guide `Post-Implementation Review` to the actual repository changes and governing documents. Use the active Small task file as the governing source when no durable document exists. Resolve required fixes through the normal task cycle. 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. ### Test Information Communication Verify acceptance-test-generator artifact paths and pass them to work-planner. ## Completion Criteria - [ ] Scope/cost evidence was collected, user-selected requirements and exclusions were confirmed, and orchestrator readiness, scale, and routing decisions were recorded - [ ] Layer routing determined (backend / frontend / fullstack) - [ ] Correct workflow followed per layer routing - [ ] codebase-analyzer included before Design Doc creation for Medium/Large flows - [ ] code-verifier discrepancies passed through Review Resolution before Design Doc review - [ ] All stopping points honored with user confirmation obtained - [ ] Quality-fixer invoked before every commit - [ ] All tasks committed or user input requested