/ln-25-architecture-diagram-builder

name: ln-25-architecture-diagram-builder
description: "Creates evidence-backed current or target architecture diagrams; not UI design."

Architecture Diagram Builder

**Goal:** Create the smallest set of understandable, evidence-backed diagrams needed to communicate current or proposed architecture. Change only approved architecture documentation; do not invent relationships, perform visual product design, replace prose evidence, audit fitness, or edit implementation.

**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 | |---|---|---| | Architecture evidence | Repository files, runtime wiring, IaC, contracts, and approved artifacts | User-provided model with `UNVERIFIED` labels | | Relationship tracing | Language intelligence, dependency tools, and focused search | Direct inspection of producers, consumers, and registrations | | Diagram format | Existing repository convention and renderer | Mermaid in Markdown, then plain ASCII | | Syntax verification | Repository renderer, parser, or preview | Manual fence, identifier, and relationship inspection | | Document mutation | Minimal patch to approved diagram artifacts | Return `BLOCKED` if path or evidence boundary is unsafe |

Diagrams communicate a model; executable behavior remains authoritative for current state. Keep current, target, and transition views visibly distinct.

Artifact Rules

• Reuse an existing diagram convention or use `docs/architecture/diagrams/<view>.md`.
• Prefer Markdown with Mermaid for text-reviewable source; use ASCII when Mermaid is unsupported.
• For static structure, choose the context, container, or component level that answers the requested question; do not create prerequisite overview diagrams when existing context suffices.
• Keep diagram source reviewable in version control.
• Split views when one diagram needs multiple unrelated stories.
• Never use color as the only carrier of meaning.
• Use stable element identifiers and concise display labels so revisions produce reviewable diffs.
• Keep detailed evidence beside the diagram rather than crowding nodes and relationships.
• Preserve an understandable existing notation; introduce a new notation only when it answers the audience question better.

Checklist

1. Establish the Diagram Contract

• [ ] Resolve audience, question, current or target state, scope, approved destination, and required notation.
• [ ] Read repository instructions, relevant architecture artifacts, and existing diagram conventions.
• [ ] Select the minimum useful view or views; reject diagrams that add no relationship clarity.
• [ ] Define the evidence boundary and label user-supplied or proposed elements separately.
• [ ] Keep the run read-only except for approved architecture diagram documentation.

2. Build t