/ln-43-code-modernizer

name: ln-43-code-modernizer
description: "Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning."

Code Modernizer

**Goal:** Modernize a bounded capability only when the new design measurably reduces human workflow friction, maintenance, risk, dependency duplication, or delivered artifact cost. Preserve behavior, isolate migrations, and revert changes that do not create net value.

**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 tool | Use it when | Fallback | |---|---|---|---| | Current mechanism and consumers | Native file search plus language server or host-native code intelligence | Mapping contracts, callers, configuration, data, lifecycle, and tests | Narrow import, symbol, route, and configuration search with direct reads | | Existing platform capabilities | Manifests, lockfiles, runtime APIs, and current official documentation | Avoiding new dependencies or custom code for an already available feature | Repository examples and source inspection; mark capability `UNVERIFIED` if current docs are unavailable | | External replacement candidates | Official package registries, source repositories, documentation, releases, advisories, and license data | Comparing maintained software with custom implementation | Primary-source web research; do not rely on popularity lists alone | | Baseline and value | Build output, bundle analysis, code inventory, benchmark, defects, or maintenance evidence | Defining what modernization must improve | Reproducible static counts with documented scope and limitations | | Safe migration | Git isolation, focused edits, native package manager, and repository generation commands | Replacing one bounded capability and its consumers | Stop if user changes or generated state cannot be protected | | Verification | Repository-defined build, lint, type, test, smoke, packaging, and runtime checks | Before migration and after every retained step | Choose the smallest portfolio action when existing evidence cannot prove a material contract | | Delivered artifact analysis | Existing bundle analyzer, size report, startup profile, or dependency report | Bundle size, load path, or runtime cost is part of the goal | Build artifact comparison with reproducible file and compression rules |

Do not replace working custom code merely because an external package exists. Do not introduce an unmaintained dependency, accept incompatible licensing, or remove the old path until all consumers and rollback conditions are understood.

Workflow Boundary

This workflow owns a measured reduction in maintenance cost. Requests primarily establishing container, access, error or recovery guarantees are technical foundation work, even when refactoring is needed. Do not turn a foundatio