/ln-22-current-architecture-documenter

name: ln-22-current-architecture-documenter
description: "Documents current architecture from implementation evidence; does not propose a target or audit fitness."

Current Architecture Documenter

**Goal:** Produce a trustworthy snapshot of the architecture implemented in the checked-out repository. Document what exists and how it behaves; do not score it, prescribe a target architecture, repair code, or turn intended diagrams into facts.

**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 | |---|---|---| | Snapshot identity and worktree state | Git status, branch, remote, and HEAD | Record the supplied snapshot as `UNVERIFIED` | | Structure and configuration | Native listing, search, manifests, and direct file reads | Narrow manual inspection | | Symbols, dependencies, and consumers | Language intelligence or resolved dependency tooling | Search definitions, registrations, imports, and callers | | Runtime and deployment topology | Entrypoints, IaC, containers, CI, configuration, and runtime evidence | Mark deployment relationships `UNKNOWN` | | Document mutation | Minimal patch to the approved architecture document | Return `BLOCKED` if no writable path is authorized |

Prefer local evidence over remote repository state. A path, diagram, or naming convention is a lead until executable wiring or an authoritative contract confirms it.

Artifact Rules

• Reuse a clear current-state architecture document; otherwise use `docs/architecture/current-state.md`.
• Anchor the document to remote, branch, HEAD, worktree state, and observation date.
• Cite material claims with file paths, symbols, commands, or configuration keys.
• Label claims `OBSERVED`, `DOCUMENTED`, `INFERRED`, or `UNKNOWN`.
• Separate actual structure from intended target design and from audit findings.
• Map the declared system scope at a coarse level first, then deepen only what explains its critical behavior; do not expand a bounded request into a repository-wide inventory.
• Prefer responsibility-oriented descriptions over exhaustive file inventories.
• Record the evidence cutoff so readers can distinguish uninspected scope from genuine absence.
• Keep volatile counts or inventories only when they affect architectural understanding.

Checklist

1. Establish the Documentation Contract

• [ ] Resolve repository scope, intended readers, approved destination, required depth, and language.
• [ ] Read repository instructions and record snapshot identity plus dirty-worktree limitations.
• [ ] Search for existing current-state, baseline, target-design, decision, diagram, and deployment artifacts.
• [ ] Reuse an unambiguous current-state document or select the default path without duplicating project knowledge.
• [ ] Keep the run read-only except for the approv