Agent skill

Ln 43 Code Modernizer

by levnikolaevich in levnikolaevich/claude-code-skills

Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.

MITAuto-check passedDevelopment

Install Ln 43 Code Modernizer

skills CLI
$ npx skills add levnikolaevich/claude-code-skills --skill ln-43-code-modernizer -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install levnikolaevich/claude-code-skills ln-43-code-modernizer --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/levnikolaevich/claude-code-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/implementation-suite/skills/ln-43-code-modernizer .claude/skills/ln-43-code-modernizer && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ln-43-code-modernizer
GitHub stars
570
Token cost
~3.9k tokens
SKILL.md length
1,933 words
Files
1
Skills in repo
31
Repo updated
First seen
Licence
MIT

At a glance

Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.

  • Works in 5 steps: Define the Modernization Target → Evaluate the Simplest Credible Design → Execute a Bounded Migration → …
  • Development work in your project
  • SKILL.md covers Tool Routing, Evidence Rules, Checklist and Self-Check, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ln 43 Code Modernizer is an agent skill from levnikolaevich/claude-code-skills. Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. The repository describes itself as: Help your AI agent finish the job: solve the right problem, keep changes focused, and show what was verified. For Claude Code and Codex. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “Use the ln-43-code-modernizer skill to moderniz a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance…”
  • “/ln-43-code-modernizer”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Define the Modernization Target
  2. Evaluate the Simplest Credible Design
  3. Execute a Bounded Migration
  4. Verify and Keep or Discard
  5. Finalize and Report

What it can do on your machine

Read from SKILL.md and the folder at commit 0ce8796. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ln 43 Code Modernizer loads about 3.9k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 1,933 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~3.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from levnikolaevich/claude-code-skills at commit 0ce8796, republished under its MIT licence (© levnikolaevich). 1,933 words, ~3,877 tokens.

Download SKILL.mdSave it as .claude/skills/ln-43-code-modernizer/SKILL.md (or your agent's skills folder).
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, tool failure, a zero exit status, or a self-reported success is not proof; only the observed outcome is. 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. When no one can answer during the run, state the exact question and apply the skill's verdict for the remaining gap instead of waiting or guessing. 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

NeedPreferred toolUse it whenFallback
Current mechanism and consumersNative file search plus language server or host-native code intelligenceMapping contracts, callers, configuration, data, lifecycle, and testsNarrow import, symbol, route, and configuration search with direct reads
Existing platform capabilitiesManifests, lockfiles, runtime APIs, and current official documentationAvoiding new dependencies or custom code for an already available featureRepository examples and source inspection; mark capability UNVERIFIED if current docs are unavailable
External replacement candidatesOfficial package registries, source repositories, documentation, releases, advisories, and license dataComparing maintained software with custom implementationPrimary-source web research; do not rely on popularity lists alone
Baseline and valueBuild output, bundle analysis, code inventory, benchmark, defects, or maintenance evidenceDefining what modernization must improveReproducible static counts with documented scope and limitations
Safe migrationGit isolation, focused edits, native package manager, and repository generation commandsReplacing one bounded capability and its consumersStop if user changes or generated state cannot be protected
VerificationRepository-defined build, lint, type, test, smoke, packaging, and runtime checksBefore migration and after every retained stepChoose the smallest portfolio action when existing evidence cannot prove a material contract
Delivered artifact analysisExisting bundle analyzer, size report, startup profile, or dependency reportBundle size, load path, or runtime cost is part of the goalBuild 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
  • Check language, runtime, framework, platform, and already-declared dependency capabilities before searching for a new package.
  • Identify obsolete compatibility paths, parallel mechanisms, unused extension points, duplicated integrations, and transitional adapters that can be removed directly.
  • For external candidates, evaluate functional fit, API stability, maintenance activity, security history, license, ownership, release cadence, size, runtime support, and ecosystem compatibility.
  • Verify candidate claims from official documentation, repository releases, advisories, and package metadata matching the intended version.
  • Inspect migration guides, breaking changes, configuration model, lifecycle, failure behavior, transitive dependencies, and exit strategy.
  • Build a semantic-gap ledger for replacement candidates: input normalization, Unicode/time/date behavior, precision, ordering, errors, cancellation, streaming, concurrency, security limits, and other edge behavior relevant to the current contract.
  • Compare retain, simplify in place, use existing platform capability, adopt external software, and remove capability where each is credible; prefer the shortest safe path that removes toil without hiding truth or control.
  • Estimate workflow steps and concepts removed, time-to-result and recovery delta, code removed, adapters added, dependency and bundle delta, migration effort, operational change, rollback difficulty, and residual lock-in where each is relevant.
  • Select the option with the best evidence-backed value-to-risk ratio, not the newest or most popular option.
  • Mark the chosen option SELECTED and every considered but non-chosen option REJECTED, recording the evidence or tradeoff that determined each decision.
  • Request user direction when licensing, public contract, persisted-data migration, vendor commitment, or irreversible operational tradeoffs change product intent; applying a migration outside a disposable environment always requires explicit authorization.
Show full SKILL.md (913 more words)Show less
3. Execute a Bounded Migration
  • Test value and boundary: Require every test to detect a concrete defect in this product's business logic and name the protected business outcome. Prefer E2E through user or external-system boundaries; use integration or unit tests only for business scenarios difficult to exercise reliably through E2E. Reject platform, trivial-wiring, implementation-detail, and duplicate proof with no distinct business failure signal.
  • Map the current external contract, important failures, and data or configuration compatibility to existing proof; implement KEEP, ADD, UPDATE, MERGE, DELETE, or justified NO_TEST within the approved test scope, remove superseded testware, and give temporary characterization or compatibility evidence a removal trigger.
  • Use differential or characterization cases on shared representative and adversarial inputs; the old implementation is comparison evidence, not the authority for known defects or explicitly changed behavior. Resolve differences against the intended contract.
  • Introduce the replacement at one clear boundary rather than mixing old and new mechanisms throughout the codebase.
  • Use native package-manager and generation commands for dependencies and generated state; do not hand-edit lockfiles or generated artifacts.
  • Update callers, types, configuration, dependency injection, routes, events, serialization, tests, build scripts, and documentation required by the bounded capability.
  • Preserve backward compatibility only where a real consumer requires it and define the removal condition for every temporary adapter.
  • Prepare and test persisted-data or configuration migrations against a disposable copy with explicit ordering, resumability, mixed-version behavior, backup/restore evidence, rollback, and failure recovery; apply them elsewhere only when the user names the target environment and authorizes the rehearsed operation.
  • Before removing a dependency or module reported as unused, check dynamic imports, reflection, plugin/config registration, code generation, build scripts, CLIs, and optional runtime paths that static import scans miss.
  • Remove the old implementation only after search and runtime wiring checks show no remaining consumer.
  • Inspect the diff for unrelated refactoring, formatting churn, duplicate dependencies, debug code, and accidental public contract changes.
4. Verify and Keep or Discard
  • Run focused contract and regression tests immediately after each migration step.
  • Run the repository's required build, lint, type, test, smoke, packaging, and application-start checks.
  • Compare the agreed workflow, maintenance, dependency, bundle, startup, performance, or defect metric with the baseline under equivalent conditions.
  • For bundle work, compare real build composition, parsed and compressed size, chunking, loading behavior, and source maps rather than package metadata alone.
  • Evaluate entrypoint and route critical paths separately: total bytes may fall while initial transfer, request waterfalls, decompression, parse/compile, execution, or cache invalidation gets worse.
  • Verify tree-shaking and deduplication claims against the actual bundler graph, module format, exports, side-effect metadata, and target browsers/runtimes before changing imports or package metadata.
  • Check security advisories, licenses, runtime support, package provenance, and new transitive dependencies for the retained design.
  • Exercise rollback or removal mechanics when migration failure would be costly or difficult to detect.
  • Mark the migration KEEP only when required behavior and verification pass and the defined net value is achieved.
  • Resolve bounded migration defects and repeat affected checks before the final decision; mark DISCARD and revert the bounded change when value remains unproven, regressions remain, or net complexity exceeds the agreed tradeoff.
  • Remove non-retained adapters, instrumentation, feature flags, packages, and generated artifacts only when their ownership is proven; clean only run-owned ledger paths and exact process IDs, preserving dirty or pre-existing worktrees and reported evidence.
5. Finalize and Report
  • Verify that no stale implementation, import, registration, configuration, documentation, or dependency remains after a kept migration.
  • Confirm relevant verification covers the final retained state, reusing still-valid results and rerunning checks invalidated by changes or unresolved failures. Compare the final diff with the original modernization scope.
  • Reconcile option and migration ledgers with final code, dependencies, measurements, and rollback state.
  • Identify residual custom code, compatibility adapters, migration steps, operational changes, and external dependency risks.
  • Bind the modernization result to the protected behavior and final implementation state; identify which prior assumptions or verification became stale.
  • Use DELIVERED when the selected bounded design is fully retained and verified; use PARTIAL when an independently safe subset is retained with explicit remaining work; use NO_CHANGE when every migration is discarded and the baseline is restored; use BLOCKED when authorization, safety evidence, or required verification is unavailable.

Self-Check

  • Reconcile before returning. Check item-level evidence, requirement coverage, contradictions, scope, verdict, and applicable cleanup. Correct the report or authorized artifacts. Reuse valid evidence; do not automatically rescan the repository or rerun successful commands. Repeat checks only for relevant changes, failures, or unresolved evidence. Disclose remaining gaps.

Output Contract

Report in the user's language, in this order; label all five fields and state each fact once. Use controlled plain language: one fact per sentence, usually under 20 words, active voice, and one term per concept, with no synonyms for verdicts, IDs, or states. Small results may use one line per field; omit empty tables and do not copy linked artifacts:

  1. Result: The exact skill-specific verdict token first, then the supported outcome.
  2. Scope: Reviewed/changed scope, exclusions, baseline, and material assumptions.
  3. Evidence: Skill-specific fields below; distinguish facts, inferences, and unverified claims. Link artifacts; use tables when useful.
  4. Verification: Checks/results, unavailable evidence, and applicable cleanup/external state.
  5. Completion: Checklist: X/Y complete; Incomplete: None or each UNPROVEN item's reason, outcome impact, and exact next action; residual risks and required decisions.

Skill-specific evidence: Capability, protected contract, consumers, current cost, and behavioral/value baselines. Compare considered alternatives and SELECTED / REJECTED reasons. Per migration: changes, verification, comparable value metrics, and KEEP / DISCARD. Include code/dependency and workflow deltas, affected test actions, residual custom code/compatibility, outstanding transition work, and run-owned measurement/diff/rollback/cleanup evidence.

© levnikolaevich, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/implementation-suite/skills/ln-43-code-modernizer of levnikolaevich/claude-code-skills.

Open the folder on GitHubat commit 0ce8796

Compare with similar skills

Ln 43 Code Modernizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ln 43 Code Modernizer compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ln 43 Code Modernizer this skilllevnikolaevich/claude-code-skills570—~3.9kAutomated safety check: PassMIT
Vercel Composition Patternssupabase/supabase111k59 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 59 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from levnikolaevich/claude-code-skills

All 31 skills in this repo
  • Ln 53 Documentation Auditor

    levnikolaevich/claude-code-skills

    Audits documentation and comments for trust, coverage, consistency and freshness; read-only.

    570 GitHub stars~3.8k tokensUpdated 3 days ago
    Auto-check passed
  • Ln 81 Skill Reviewer

    levnikolaevich/claude-code-skills

    Reviews skill instructions, trigger boundaries and distribution contracts; not product code.

    570 GitHub stars~3.5k tokensUpdated 3 days ago
    Auto-check passed
  • Ln 11 Opportunity Evaluator

    levnikolaevich/claude-code-skills

    Evaluates new product opportunities through demand, channels and economics before committing to build.

    570 GitHub stars~3k tokensUpdated 3 days ago
    Auto-check passed
  • Ln 12 Product Requirements Builder

    levnikolaevich/claude-code-skills

    Defines product requirements, business rules and acceptance criteria for a committed intent; edits product docs only.

    570 GitHub stars~1.9k tokensUpdated 3 days ago
    Auto-check passed
  • Ln 13 Interaction Design Builder

    levnikolaevich/claude-code-skills

    Designs user flows, interaction states and mockups for a defined product scope; does not implement UI code.

    570 GitHub stars~1.8k tokensUpdated 3 days ago
    Auto-check passed
  • Ln 21 System Design Baseline Builder

    levnikolaevich/claude-code-skills

    Defines measurable architecture drivers and constraints before system design; edits architecture docs only.

    570 GitHub stars~2.5k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Ln 43 Code Modernizer

What does Ln 43 Code Modernizer do?

Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning. Ln 43 Code Modernizer is an agent skill from levnikolaevich/claude-code-skills. Modernizes a bounded capability to reduce demonstrated maintenance cost; not routine upgrades or performance tuning.

When should I use Ln 43 Code Modernizer?

Ln 43 Code Modernizer fits situations like: development work in your project.

How do I install Ln 43 Code Modernizer in Claude Code?

Run `npx skills add levnikolaevich/claude-code-skills --skill ln-43-code-modernizer -a claude-code`. Or copy the skill folder (plugins/implementation-suite/skills/ln-43-code-modernizer in levnikolaevich/claude-code-skills) into .claude/skills/ln-43-code-modernizer in your project. Claude Code loads it when a task matches its description.

How do I install Ln 43 Code Modernizer in Codex?

Run `npx skills add levnikolaevich/claude-code-skills --skill ln-43-code-modernizer -a codex`. Or copy the skill folder (plugins/implementation-suite/skills/ln-43-code-modernizer in levnikolaevich/claude-code-skills) into .agents/skills/ln-43-code-modernizer in your project. Codex loads it when a task matches its description.

Can I use Ln 43 Code Modernizer in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add levnikolaevich/claude-code-skills --skill ln-43-code-modernizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ln-43-code-modernizer, .gemini/skills/ln-43-code-modernizer, .github/skills/ln-43-code-modernizer and .opencode/skills/ln-43-code-modernizer in your project.

What does Ln 43 Code Modernizer need to run?

SKILL.md names no scripts, command-line tools or credentials: Ln 43 Code Modernizer is instructions for the agent only.

Does Ln 43 Code Modernizer access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ln 43 Code Modernizer safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ln 43 Code Modernizer use?

Ln 43 Code Modernizer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ln 43 Code Modernizer use?

About 3.9k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ln 43 Code Modernizer?

Skills that share tags, products or a category with Ln 43 Code Modernizer: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 296k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ln 43 Code Modernizer?

levnikolaevich (a GitHub user) maintains it in levnikolaevich/claude-code-skills, which has 570 GitHub stars. The repository holds 31 skills in this directory. The repository was last updated on October 5, 2026.

Source: levnikolaevich/claude-code-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.