dsh-modernize-code
Run the following command in DeepSeek Harness:
dsh plugin install 988hj7tczd-oss/dsh-modernize-code
Paste the following prompt into your AI chat to install this plugin:
Install this plugin in DeepSeek Harness by running dsh plugin install 988hj7tczd-oss/dsh-modernize-code; the source repository is available at https://github.com/988hj7tczd-oss/dsh-modernize-code .
About this plugin
Modernizing a legacy codebase often feels binary: do nothing, or attempt a big-bang rewrite. What is missing in between is a disciplined process—environment validation, hotspot identification, and a staged roadmap with rollback points. dsh-modernize-code structures that process into four stages: preflight (environment readiness), assess (static legacy-pattern scanning ranked by impact, risk, and cost), map (a phased migration roadmap), and transform (incremental, block-by-block refactoring with per-stage rollback points and user-confirmed edits).
Every stage produces a concrete artifact: PREFLIGHT.md, legacy-hotspots.md, and MIGRATION_ROADMAP.md. Unanswered questions are preserved verbatim as open items—never silently dropped or answered on your behalf. The plugin runs fully offline, touches only the scanned project directory, and requires no network access or credentials.
It is built for engineering teams maintaining large legacy systems, architects who need an auditable roadmap for leadership, and solo developers who want to embed disciplined code-modernization checks into a DeepSeek Harness agent workflow.
Use Cases
- Staged modernization of large-scale legacy systems
- Pre-migration environment readiness and code-health assessment
- Building an auditable, phased migration roadmap for technical debt
Best For
- Engineering teams maintaining large legacy codebases
- Architects needing an auditable roadmap for stakeholders
- Developers embedding modernization workflows into DeepSeek Harness agents
Related Plugins
A method pack that makes AI coding agents plan against your real baseline, prove completion with fresh evidence, and reduce reworks and unsafe changes.
Turns the DeepSeek Harness session into a captain that builds a durable sub-agent team, splits goals into dependency-aware tasks, and coordinates work via direct messages and a live Web UI.
Gives coding agents design judgment, letting Claude Code, Cursor, and 70+ agents generate and iterate high-quality UI, presentations, and graphics right from the terminal.
Run the Pi ecosystem's plugins on DeepSeek Harness, unmodified, via a compatibility layer that implements Pi's public extension ABI on DSH's native services.