Playbook
0 / 10 complete0%
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05
  6. 06
  7. 07
  8. 08
  9. 09
  10. 10
Step 01 of 10 6-12 weeks· advanced

Step 1: Audit and Inventory

Inventory programs, service programs, modules, CL programs, DDS / SQL files, display files (5250), job streams, data, environment dependencies, and people.

What you're doing in this step

Produce a comprehensive IBM i inventory: RPG programs (II/III/IV, batch/interactive/service), service programs (*SRVPGM) with exported procedures, modules, CL programs, DDS/SQL physical and logical files, display files with subfile complexity, scheduled jobs, journaled data, library list / authority structure, and people (skills + retirement timeline). Use IBM i analysis tools (X-Analysis, ARCAD, AveriSource, IBM ADDI) to accelerate.

Recommended prompts

Use one of these to do the work in your IDE

Open the template to read it in full. Click Copy prompt to grab it (with your stack values pre-filled where they apply) — then paste into Claude Code, Cursor, or wherever you build.

Primary recommendation 2-4 hours

Legacy System Audit

Reverse-engineer an existing application: structure, dependencies, integrations, business logic, hidden risks. The starting point for any migration.

View template
Template· Template varies (per program)

RPG Business Rule Extraction

Extract business rules from RPG II/III/IV programs into a structured catalog — handling indicators, cycle programs, and the procedural patterns of IBM i development.

Use this when: Pulling rules out of representative programs as part of the audit

rpgibm-i
View template
Template· Template 1-2 days per major job stream

AS/400 CL Program Decomposition

Decompose CL (Control Language) programs and job streams into modern orchestration — Spring Batch, Step Functions, Airflow, or message-driven architectures.

Use this when: CL job streams need decomposition into target-runtime equivalents (Spring Batch / Step Functions / Airflow)

rpgibm-ijavadotnet
View template
Template· Template 1-2 days per major schema

DB2 for i to Relational Database Mapping

Map DB2 for i schemas (with multi-member files, logical files, journaling, DDS extensions) to a modern relational database — Postgres, SQL Server, or Azure SQL.

Use this when: Inventorying the DB2 for i schema as part of the audit

ibm-irpgpostgressql
View template
Recommended skills

Drop these into Claude Code for this phase

Skills auto-trigger on the right kind of request. Install once; they apply to every prompt that fits.

Skill· Skill 5 min setup

Legacy Code Analyzer Skill

Claude Code skill that reads legacy .NET code (WebForms, VB.NET, classic ASP) and explains what it does — the foundation for any migration.

claude-codedotnet
View skill
Skill· Skill 5 min setup

Migration Planner Skill

Flagship migration skill that walks Claude Code through audit → strategy → slicing → cutover for any legacy system migration.

claude-code
View skill
Recommended MCP configs

Wire these tools into Claude Code first

MCP servers give Claude Code direct access to external systems (Jira, browsers, databases). Configure once.

MCP config· MCP config 5 min setup

Filesystem MCP for Evoke

Pre-configured filesystem MCP server for Claude Code — safe, scoped read/write access to project files.

claude-codemcp
View config
MCP config· MCP config 10 min setup

Postgres MCP for Evoke

Pre-configured Postgres MCP server for Claude Code — schema inspection and read-only queries to make database work safer and faster.

claude-codemcppostgres
View config
MCP config· MCP config 10 min setup

Confluence MCP for Evoke

Pre-configured Atlassian Confluence MCP server for Claude Code — search, read, and write internal documentation pages from chat.

claude-codemcp
View config
When you're done

Verify these in your own work before moving on

This is a checklist for you to mentally tick off in your repo and IDE — the site doesn't track it, you do.

  • Complete program inventory (RPG, CL, modules)
  • Service program / module inventory with exported procedures
  • CL program inventory with orchestration map
  • File inventory (PF, LF, display, print)
  • Display file complexity assessment (subfile usage, conditioning indicators)
  • Database schema documented
  • Job scheduler dependencies
  • Environment dependencies (authority, library list)
  • Workforce assessment with retirement timeline
  • Risk register with IBM i-specific risks
  • Strategic recommendation confirmed (rewrite vs replatform vs refactor vs replace)
Common pitfalls

What goes wrong at this step

  • Underestimating display file count — each business workflow often has its own display file with 5-15 record formats
  • Missing service programs — modular RPG uses service programs heavily; map exported procedures
  • Skipping DDS analysis — older shops have heavy DDS investment; field metadata matters for migration
  • Trusting documentation — almost always incomplete
  • Not running automated analysis — manual analysis of 1M+ LOC takes too long
← Back to intake

Command Palette

Search for a command to run...