/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:** The checklist defines completion. Track each item internally as `PENDING`, `PROVEN` with evidence, `CLEARED` with evidence its condition is absent, or `UNPROVEN` with a gap; reading, delegation, or tool failure is 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, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. Scale depth to material risk without skipping checks. Preserve dependency and safety order; otherwise choose an appropriate verification method. Accept equivalent user or repository evidence; no other skill, named artifact, or complete lifecycle is required. Preserve source requirement and decision IDs. Bind reused evidence to relevant source versions, dirty changes, configuration, and environment; invalidate only affected claims. On continuation, reconcile task, authorization, current state, and unresolved evidence. For long work, return a compact continuation record or update an already authorized artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and external-action authority. Prepare authorized work before required approval. If blocked by an instruction, cite its exact source and unresolved boundary; do not invent approval gates from caution.

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.

Evidence Rules

• Compare net system complexity: removed code and risk minus new dependency, adapter, operational, and migration costs.
• External candidate claims require current primary evidence for maintenance, security, license, runtime support, and API fit.
• Bundle or performance value requires comparable measurements; line-count reduction alone does not prove a better design.
• Preserve public behavior unless the request explicitly authorizes a contract migration.

Checklist

1. Define the Modernization Target

• [ ] Resolve the bounded capability, protected outcome, current pain, affected users, developers, or operators, success metric, constraints, and explicit non-goals; label unsupported intent inferences.
• [ ] Read repository instructions and inspect Git state, generated files, package-manager policy, and current user changes.
• [ ] Inventory the current implementation, public contracts, consumers, configuration, persisted data, runtime registration, tests, and operational procedures.
• [ ] Identify the specific workflow, maintenance, security, compatibility, duplication, bundle, startup, or delivery cost that must improve.
• [ ] Establish behavioral and relevant quantitative baselines before changing code; for human workflows use reproducible observations such as required steps or concepts, time to first meaningful result, error comprehension, and recovery effort.
• [ ] Isolate the work so each migration step can be reverted without touching unrelated or user-owned changes.
• [ ] **Run-owned resources:** Start a run-owned resource ledger with every created absolute path, worktree, process ID, cache, report, and temporary artifact; never register pre-existing resources as cleanup targets.
• [ ] Use `NO_CHANGE` when evidence shows no worthwhile in-scope modernization; use `BLOCKED` when a plausible requested benefit cannot be evaluated because essential evidence is unavailable.

2. Evaluate the Simplest Credible Design

• [ ] Chec