claudecodex

code-modernization

面向任何遗留代码库的引导式现代化:从 /modernize 开始,获得评估、交互式地图、从代码中挖掘出的业务规则,以及一份由你审批的计划,然后进行升级、重写或重建,并附带独立验证,证明新代码的行为与旧代码一致。包含安全加固、一页纸报告、专家智能体,以及可选的实时进度面板(早期访问)。

2 on GitHubby Anthropicv1.0.0Apache-2.0updated yesterdaydeveloper-tools
/

Plugin code-modernization from marketplace kael-odin-plugins-zh in kael-odin/claude-plugins-zh. Commands read from the repo's manifest — today.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Slash commands (13)

  • /code-modernization:modernize-assess

    What am I dealing with? Inventory, complexity, debt, security and a recommended modernization pattern

  • /code-modernization:modernize-brief

    Write the phased Modernization Brief — the plan a steering committee approves and the build commands execute against

  • /code-modernization:modernize-extract-rules

    Mine the business rules out of the code into testable Given/When/Then rule cards with file:line citations

  • /code-modernization:modernize-harden

    Security scan of the legacy system with a reviewable remediation patch (OWASP, CWE, CVEs, secrets, injection)

  • /code-modernization:modernize-map

    Show me the structure — dependencies, data flow, entry points and business flows, as an interactive map

  • /code-modernization:modernize-preflight

    Run this first — checks the environment, records where the code lives, and says what to fix before anything else runs

  • /code-modernization:modernize-reimagine

    Rebuild the system from its extracted intent on a new architecture, with two human checkpoints

  • /code-modernization:modernize-review

    Confirm or correct the business rules that need a person's judgement; the plan and the build read your answers

  • /code-modernization:modernize-status

    Where am I? Progress, what is stale, and the exact next command to run — start here when unsure

  • /code-modernization:modernize-transform

    Rewrite one legacy module in the target stack, with tests that prove it behaves the same

  • /code-modernization:modernize-uplift

    Same-stack version uplift (e.g. .NET Framework 4.8 to .NET 8, Java 8 to 17) — keep the code, fix the version deltas, prove nothing changed

  • /code-modernization:modernize-verify

    Prove the modernized code behaves like the legacy, with an independent re-check and one verdict per module

  • /code-modernization:modernize

    Start here — say what you want done with your code and get the plan and the first step

Subagents (8)

  • architecture-critic

    Reviews proposed target architectures and transformed code against modern best practice. Adversarial — looks for over-engineering, missed requirements, and simpler alternatives.

  • business-rules-extractor

    Mines domain logic, calculations, validations, and policies from legacy code into testable Given/When/Then specifications. Use when you need to separate "what the business requires" from "how the old code happened to implement it.

  • legacy-analyst

    Deep-reads legacy codebases (COBOL, Java, .NET, Node, anything) to build structural and behavioral understanding. Use for discovery, dependency mapping, dead-code detection, and "what does this system actually do" questions.

  • scaffolder

    Scaffolds one service of a reimagined system from the approved architecture and spec — project skeleton, domain model, API stubs, executable acceptance tests. Write access is scoped to its own service directory under modernized/.

  • security-auditor

    Adversarial security reviewer — OWASP Top 10, CWE, dependency CVEs, secrets, injection. Use for security debt scanning and pre-modernization hardening.

  • test-engineer

    Writes characterization, contract, and equivalence tests that pin down legacy behavior so transformation can be proven correct. Use before any rewrite.

  • uplift-migrator

    Migrates ONE project/module of an in-flight same-stack version uplift by applying a proven pilot playbook — minimal diff, then runs that unit's real build to prove it. Refuses to migrate anything if no playbook exists yet. Write access is scoped to its own unit's directory inside the uplift working

  • version-delta-analyst

    Identifies the breaking changes between two versions of the SAME stack (e.g. .NET Framework 4.8 → .NET 8, Java 8 → 17/21, Spring Boot 2 → 3) that actually bite a given codebase, and drives the ecosystem's migration tooling. Use for same-stack uplifts, where code is preserved and tweaked — not rewrit

Hooks (6)

  • UserPromptSubmit

    sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" command

  • Stop

    sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" state

  • Stop

    sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" run

  • SessionStart

    sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" health

  • PostToolUseFailure

    sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" failure

  • StopFailure

    sh "${CLAUDE_PLUGIN_ROOT}/scripts/telemetry.sh" failure

View source on GitHub kael-odin.github.io

More from kael-odin/claude-plugins-zh

All 319 plugins →

azure

claudecodex

将 Claude 打造成 Azure 专家。本插件集成了 Azure MCP server 和专业 Azure skills,助你摆脱泛泛而谈的建议。它让 Claude 能够执行实际任务:列出资源、验证部署、诊断基础设施问题,并优化 50+ 项 Azure 服务的成本。

44 skills · 1 MCP server

2

cockroachdb

claudecodex

将 Claude Code 直接连接到你的 CockroachDB 集群,进行实操数据库工作——探索 schema、编写优化的 SQL、调试查询,并管理分布式数据库集群。该插件提供 14 个工具,涵盖两个活跃的 MCP 后端(自托管 MCP Toolbox 和托管式 CockroachDB Cloud MCP Server)、三个专用 agent(DBA、Developer、Operator)、覆盖 6 个运维领域的 32 个 skill,以及内置安全 hook。

34 skills · 3 agents · 3 MCP servers · hooks

2

databricks

claudecodex

面向 CLI、Apps、Lakebase、Model Serving、Lakeflow Jobs、Spark Declarative Pipelines、Declarative Automation Bundles(DAB)以及经典版到无服务器迁移的 Databricks skill。

37 skills · 2 commands · hooks

2

clay

claudecodex

在 Claude Code 中使用 Clay:设置并登录 clay CLI,查询和分析 Clay 表格,在 Clay 的 GTM 数据库中搜索人员和公司,管理受众、信号、例程和工作流,并起草和审阅 Sequencer 营销活动。包含自动批准该插件自身 clay CLI 调用和 Clay skills 的 hooks;需要 Clay 账户。

38 skills · hooks

2

amplitude

claudecodex

将 Amplitude 作为专业分析工具使用——埋点接入 Amplitude、发现产品机会、分析图表、创建仪表盘、管理实验,并洞察用户与账户。

36 skills · 1 MCP server

2

data-agent-kit

claudecodex

本插件为在 Google Cloud 上工作的数据工程师与数据库从业者提供一套专用技能,相当于一位专家助手:在常用的编码代理里用自然语言描述需求,即可设计复杂的数据管道、用 dbt 转换数据、编写 Spark 与 BigQuery SQL 笔记本,并在 GCP 数据生态中编排端到端工作流。

37 skills

2

Similar plugins

Scaffold, validate, and publish new Claude Code plugins with proper structure

3 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

slidev

claude

Claude Code skill for creating and presenting Slidev slidedecks

1 skill

slidevjs/slidev 49,452

Observability plugin for Claude Code with MLflow tracing

mlflow/mlflow 28,788

deepeval

claude

Skills for adding DeepEval evaluations, tracing, datasets, Confident AI reports, and iterative improvement loops to AI applications.

3 skills

confident-ai/deepeval 19,466

arize-phoenix

claudecodex

Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.

1 MCP server

Arize-ai/phoenix 12,267

treg

claudecodex

OpenRouter for tools - 4,000+ agent-friendly tools, pay for the usage, not subscription

1 skill · 1 MCP server

superdesigndev/treg 7,890

Maintain code-modernization?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins319 plugins