legacy-modernizer

legacy-modernizer is a skill for Claude Code from Jeffallan/claude-skills. It costs 69 tokens per session (1,269 once invoked), scanned A, original, MIT.

A planning guide for gradually updating old software systems while keeping existing behaviour working. It maps dependencies, finds service boundaries, and lays out migration steps.

In plain words
What is it for?
Assessing legacy code, planning framework upgrades, splitting a monolith into services, and designing a gradual migration with rollback points.
Why use it?
Modernising an old system all at once can cause outages and make it hard to find the source of problems.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fullstack-dev-skills plugin — 57 skills shipped together

not rated 11krepo +76 1mo ago A scan Socket: passSnyk: passSkillSpector: pass 69 tokens original MIT

Good fit Assessing legacy code, planning framework upgrades, splitting a monolith into services, and designing a gradual migration with rollback points.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffallan/claude-skills/legacy-modernizer
About the project

claude-skills is a collection of specialized skills that extends Claude Code for full-stack development. Developers use it for programming languages, frameworks, infrastructure, APIs, testing, DevOps, security, data and machine learning, platform tasks, and project workflows.

Jeffallan/claude-skills · 11,426 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Jeffallan/claude-skills --skill legacy-modernizer
Clone the repo
git clone --depth 1 https://github.com/Jeffallan/claude-skills

Made for: Claude Code.

Or install fullstack-dev-skills, the plugin that ships this one along with the rest of its 57 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for legacy-modernizer

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffallan/claude-skills/legacy-modernizer/github.svg)](https://agentmods.dev/skills/jeffallan/claude-skills/legacy-modernizer)
Your own site
<a href="https://agentmods.dev/skills/jeffallan/claude-skills/legacy-modernizer"><img src="https://agentmods.dev/badge/skills/jeffallan/claude-skills/legacy-modernizer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for legacy-modernizer

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffallan/claude-skills/legacy-modernizer"><img src="https://agentmods.dev/badge/skills/jeffallan/claude-skills/legacy-modernizer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,269 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 30 Apr 2026
  • Snyk pass 30 Apr 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00069 $0.01269
Opus 5 $0.00034 $0.00634
Sonnet 5 $0.00014 $0.00254
Haiku 4.5 $0.00007 $0.00127

Measured 12d ago against content hash 0d2258af837c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

legacy-modernizer scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

return self._new.fetch(order_id)
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/legacy-modernizer/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Legacy Modernizer

Core Workflow

  1. Assess system — Analyze codebase, dependencies, risks, and business constraints. Produce a dependency map and risk register before proceeding.

    • Validation checkpoint: Confirm all external integrations and data contracts are documented before moving to step 2.
  2. Plan migration — Design an incremental roadmap with explicit rollback strategies per phase. Reference references/system-assessment.md for code analysis templates.

    • Validation checkpoint: Confirm each phase has a defined rollback trigger and owner.
  3. Build safety net — Create characterization tests and monitoring before touching production code. Target 80%+ coverage of existing behavior.

    • Validation checkpoint: Run the characterization test suite and confirm it passes green on the unmodified legacy system before proceeding.
  4. Migrate incrementally — Apply strangler fig pattern with feature flags. Route traffic via a facade; shift load gradually.

    • Validation checkpoint: Verify error rates and latency metrics remain within baseline thresholds after each traffic increment (e.g., 5% → 25% → 50% → 100%).
  5. Validate & iterate — Run full test suite, review monitoring dashboards, and confirm business behavior is preserved before retiring legacy code.

    • Validation checkpoint: New code must be proven stable at 100% traffic for at least one release cycle before legacy path is removed.

Reference Guide

Load detailed guidance based on context:

Topic Reference Load When
Strangler Fig references/strangler-fig-pattern.md Incremental replacement, facade layer, routing
Refactoring references/refactoring-patterns.md Extract service, branch by abstraction, adapters
Migration references/migration-strategies.md Database, UI, API, framework migrations
Testing references/legacy-testing.md Characterization tests, golden master, approval
Assessment references/system-assessment.md Code analysis, dependency mapping, risk evaluation

Read the full file on GitHub · 140 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 140 lines · 69 tokens per session scan A 0d2258af837c

Subscribe to this mod's changes

legacy-modernizer is a skill published in the GitHub repository Jeffallan/claude-skills (11,426 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 1,269 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

dotnet-graphql

Guides implementation of GraphQL with HotChocolate in .NET 8 projects following Clean Architecture. Creates the GraphQL project with single or multi-schema design, queries returning IQueryable for EF Core optimization, type extensions for computed fields, field hiding, error logging, and DI registration. Use when…

landim32/awesome-ai-skills · 79 tokens

nnews-guide

Guides how to integrate the NNews NuGet package for consuming the NNews CMS API in a .NET 8 project. Use when the user wants to consume articles, categories, tags, images, or AI-powered content generation from the NNews API.

landim32/awesome-ai-skills · 56 tokens

dotnet-architecture

Guides implementation of Clean Architecture in .NET projects. Covers all layers: DTO, Domain (Models, Services, Enums), Infra.Interfaces (Repository, AppServices), Infra (Context, Repository, AppServices), and Application (DI/Startup). Use when creating entities, services, repositories, or restructuring architecture.…

landim32/awesome-ai-skills · 82 tokens

dotnet-multi-tenant

Implements Multi-Tenant pattern in .NET APIs with per-tenant database isolation, per-tenant JWT secrets, ACL layer with automatic TenantId propagation via DelegatingHandler, and dynamic DbContext factory. Covers TenantMiddleware, TenantContext, TenantResolver, TenantHeaderHandler, TenantDbContextFactory, and dynamic…

landim32/awesome-ai-skills · 72 tokens

ztools-guide

Guides how to integrate the zTools package for ChatGPT, DALL-E image generation, file upload (S3), slug generation, email sending, and document validation in a .NET 8 project. Use when the user wants to use AI features, upload files, generate slugs, send emails, or understand zTools integration.

landim32/awesome-ai-skills · 72 tokens

nauth-guide

Guides how to integrate the NAuth package for user authentication in a .NET 8 project. Use when the user wants to add authentication, configure NAuth, use IUserClient, or understand the NAuth authentication flow.

landim32/awesome-ai-skills · 49 tokens