/ln-23-system-design-proposal-builder

name: ln-23-system-design-proposal-builder
description: "Designs target system boundaries, contracts and tradeoffs from requirements; does not plan tasks or implement."

System Design Proposal Builder

**Goal:** Create a proportionate, evidence-backed target system design that turns requirements into explicit boundaries, contracts, data flow, failure behavior, operations, and tradeoffs. Change only the approved design document; do not implement, audit, or approve the delivery.

**Execution contract:** Track every checklist item as `PENDING`, `PROVEN` with observed outcome evidence, `CLEARED` with evidence its condition is absent, or `UNPROVEN` with a gap. Reading, delegation, tool failure, zero exit status, and self-reported success are not proof. Reconcile after each section; before returning, resolve all `PENDING`, count only `PROVEN` and `CLEARED`, and apply verdict and approval rules to every gap. Preserve intent, scope, mode, and existing authorization. Complete authorized work before required external approval; ask only consequential unresolved choices. If nobody can answer, report the exact question and apply the skill's gap verdict without waiting or guessing. Cite any blocking instruction and unresolved boundary; never invent approval gates. Scale depth to material risk; preserve mandatory checks, dependencies, and safety order while choosing verification methods. Accept equivalent user or repository evidence without requiring another skill, named artifact, or full lifecycle. Preserve source requirement and decision IDs. Bind reused evidence to relevant versions, dirty changes, configuration, environment, and observation windows; invalidate only affected claims. Choose the primary workflow by outcome and explicit selection. Consume neighboring contracts and valid evidence without duplicating ownership or restarting audits. Split distinct deliverables by scope, not mandatory skill invocation. Broad independent assessments use audit workflows; focused domain reviews remain read-only. On continuation, reconcile task, authorization, state, and gaps. Return a compact continuation record for long work or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Trace applicable requirements to their authoritative owner, planned or implemented change, acceptance evidence and status in the existing artifact or response; no new registry is required. Explicit constraints remain binding until an authorized deviation; risk determines priority, not permission to ignore them. Investigate the causal flow beyond initially named files. Within implementation authority, include structural repair needed for the outcome; minimize total complexity and risk, not changed lines. This does not authorize unrelated cleanup or mutation during review. Before retrieval, define the evidence question; read selectively without skipping applicable instructions. Use tools for mechanical processing; summarize bounded results, errors, coverage, and source paths, keeping full output outside context. Before technical decisions, establish applicability and actual versions; verify version-dependent assumptions against official documentation or specifications. Search and read primary pages for current external recommendations; snippets are not evidence. Version-matched bundled documentation or valid prior evidence suffices. Record decision, version, source, and limitations. Mark unavailable evidence UNVERIFIED; block only essential dependent work. Prefer native mechanisms, justify added tools or abstractions with evidence, and reuse the existing rule owner.

Tool Routing

| Need | Preferred capability | Fallback | |---|---|---| | Requirements and constraints | Approved requirements, baseline, decisions, and direct stakeholder input | Mark material gaps and ask the smallest decision question | | Current implementation and conventions | Repository search, manifests, entrypoints, and architecture artifacts | Treat as greenfield only when the user or repository establishes that fact; otherwise mark current state `UNKNOWN` and return `INCOMPLETE` or `BLOCKED` when the gap can change boundaries, compatibility, or migration | | External capabilities and limits | Current official documentation and specifications | Mark claims `UNVERIFIED`; avoid vendor-dependent commitment | | Estimates | Reproducible arithmetic from sourced workload assumptions | Use ranges and sensitivity; never present estimates as measurements | | Document mutation | Minimal patch to the approved target-design artifact | Return `BLOCKED` if scope or path is unsafe |

Use patterns as candidate solutions, not goals. Introduce infrastructure only when a requirement, failure mode, ownership boundary, or measured horizon pays for its lifecycle cost.

Workflow Boundary

This workflow owns structural alternatives and target system boundaries. Technical foundation work applies accepted decisions; it must not silently redesign the architecture. Link existing technical contracts instead of copying their checklists into the design.

Artifact Rules

• Reuse a clear target-design document; otherwise use `docs/architecture/target-design.md`.
• Read available baseline, current-state, decision, interface, diagram, and migration artifacts by path; none is mandatory.
• Label facts, assumptions, estimates, proposed decisions, and unresolved choices separately.
• Prefer reversible choices and the simplest topology fitting the system. For a new application, consider a modular monolith before independent services; do not force that shape onto libraries, plugins, or an established topology.
• Do not silently change an accepted decision; record the conflict and required governance action.

Checklist

1. Frame the Design

• [ ] Resolve business outcome, actors, journeys, scope, non-goals, horizon, readers, language, and the approved canonical destination befo