accessibility-audit
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits,…
Orchestrate legacy system modernization using the strangler fig pattern with gradual component replacement
$ npx -y skills add wshobson/agents --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/legacy-modernizeContext preview
What this command does when you run it.
Orchestrate legacy system modernization using the strangler fig pattern with gradual component replacement
description: "Orchestrate legacy system modernization using the strangler fig pattern with gradual component replacement" argument-hint: "<legacy codebase path or description> [--strategy parallel-systems|big-bang|by-feature|database-first|api-first]"
You MUST follow these rules exactly. Violating any of them is a failure.
1. **Execute steps in order.** Do NOT skip ahead, reorder, or merge steps. 2. **Write output files.** Each step MUST produce its output file in `.legacy-modernize/` before the next step begins. Read from prior step files — do NOT rely on context window memory. 3. **Stop at checkpoints.** When you reach a `PHASE CHECKPOINT`, you MUST stop and wait for explicit user approval before continuing. Use the AskUserQuestion tool with clear options. 4. **Halt on failure.** If any step fails (agent error, test failure, missing dependency), STOP immediately. Present the error and ask the user how to proceed. Do NOT silently continue. 5. **Use only local agents.** All `subagent_type` references use agents bundled with this plugin or `general-purpose`. No cross-plugin dependencies. 6. **Never enter plan mode autonomously.** Do NOT use EnterPlanMode. This command IS the plan — execute it.
Before starting, perform these checks:
Check if `.legacy-modernize/state.json` exists:
Found an in-progress legacy modernization session: Target: [target from state] Current step: [step from state] 1. Resume from where we left off 2. Start fresh (archives existing session)
Create `.legacy-modernize/` directory and `state.json`:
{
"target": "$ARGUMENTS",
"status": "in_progress",
"strategy": "parallel-systems",
"current_step": 1,
"current_phase": 1,
"completed_steps": [],
"files_created": [],
"started_at": "ISO_TIMESTAMP",
"last_updated": "ISO_TIMESTAMP"
}Parse `$ARGUMENTS` for `--strategy` flag. Use `parallel-systems` as default if not specified.
Extract the target description from `$ARGUMENTS` (everything before the flags). This is referenced as `$TARGET` in prompts below.
---
Use the Task tool with subagent_type="framework-migration-legacy-modernizer":
Task:
subagent_type: "framework-migration-legacy-modernizer"
description: "Analyze legacy codebase for modernization readiness"
prompt: |
Analyze the legacy codebase at $TARGET. Document a technical debt inventory including:
- Outdated dependencies and deprecated APIs
- Security vulnerabilities and performance bottlenecks
- Architectural anti-patterns
Generate a modernization readiness report with:
- Component complexity scores (1-10)
- Dependency mapping between modules
- Database coupling analysis
- Quick wins vs complex refactoring targets
Write your complete assessment as a single markdown document.Save the agent's output to `.legacy-modernize/01-legacy-assessment.md`.
Update `state.json`: set `current_step` to 2, add `"01-legacy-assessment.md"` to `files_created`, add step 1 to `completed_steps`.
Read `.legacy-modernize/01-legacy-assessment.md` to load assessment context.
Use the Task tool with subagent_type="framework-migration-architect-review":
Task:
subagent_type: "framework-migration-architect-review"
description: "Create dependency graph and integration point catalog"
prompt: |
Based on the legacy assessment report below, create a comprehensive dependency graph.
## Legacy Assessment
[Insert full contents of .legacy-modernize/01-legacy-assessment.md]
## Deliverables
1. Internal module dependencies
2. External service integrations
3. Shared database schemas and cross-system data flows
4. Integration points requiring facade patterns or adapter layers during migration
5. Circular dependencies and tight coupling that need resolution
Write your complete dependency analysis as a single markdown document.Save the agent's output to `.legacy-modernize/02-dependency-map.md`.
Update `state.json`: set `current_step` to 3, add step 2 to `completed_steps`.
Read `.legacy-modernize/01-legacy-assessment.md` and `.legacy-modernize/02-dependency-map.md`.
Use the Task tool with subagent_type="general-purpose":
Task:
subagent_type: "general-purpose"
description: "Evaluate business impact and create migration roadmap"
prompt: |
You are a business analyst specializing in technology transformation and risk assessment.
Evaluate the business impact of modernizing each component identified in the assessment and dependency analysis below.
## Legacy Assessment
[Insert contents of .legacy-modernize/01-legacy-assessment.md]
## Dependency Map
[Insert contents of .legacy-modernize/02-dependency-map.md]
## Deliverables
1. Risk assessment matrix considering: business criticality (revenue impact), user traffic patterns, data sensitivity, regulatory requirements, and fallback complexity
2. Prioritized components using weighted scoring: (Business Value x 0.4) + (Technical Risk x 0.3) + (Quick Win Potential x 0.3)
3. Rollback strategies for each component
4. Recommended migration order
Write your complete business impact analysis as a single markdown document.Save the agent's output to `.legacy-modernize/03-business-impact.md`.
Update `state.json`: set `current_step` to "checkpoint-1", add step 3 to `completed_steps`.
---
Production-ready agentic workflow building blocks: 94 plugins, 202 agents, 183 skills, 105 commands — built for Claude Code and consumed natively by OpenAI Codex CLI, Cursor, OpenCode, the Antigravity CLI, GitHub Copilot, and Pi from a single Markdown source.
Repo: wshobson/agents
You are an accessibility expert specializing in WCAG compliance, inclusive design, and assistive technology compatibility. Conduct comprehensive audits,…
Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.
The Multi-Agent Optimization Tool is an advanced AI-driven framework designed to holistically improve system performance through intelligent, coordinated…
Debug issues using competing hypotheses with parallel investigation by multiple agents
Task delegation dashboard for managing team workload, assignments, and rebalancing
Develop features in parallel with multiple agents using file ownership boundaries and dependency management