pli-migration-analyzer

pli-migration-analyzer is a skill for Claude Code, Codex from DauQuangThanh/hanoi-rainbow. It costs 106 tokens per session (1,277 once invoked), scanned A, original, MIT.

A tool for examining PL/I, an older programming language often used in mainframe systems, and planning its conversion to Java. It identifies program logic, data structures, procedures, file operations, error handling, and dependencies, then produces migration reports and Java design guidance.

In plain words
What is it for?
Use it to find PL/I source files, extract their structure and dependencies, estimate migration effort, and map procedures, data structures, and file handling to Java designs.
Why use it?
It reduces the manual work of understanding large legacy programs before rewriting them. The reports help reveal what the old code does and what the Java version needs to implement.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to find PL/I source files, extract their structure and dependencies, estimate migration effort, and map procedures, data structures, and file handling to Java designs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer
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 DauQuangThanh/hanoi-rainbow --skill pli-migration-analyzer
Clone the repo
git clone --depth 1 https://github.com/DauQuangThanh/hanoi-rainbow

Made for: Claude Code, Codex.

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 pli-migration-analyzer

README.md
[![agentmods](https://agentmods.dev/badge/skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer/github.svg)](https://agentmods.dev/skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer)
Your own site
<a href="https://agentmods.dev/skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer"><img src="https://agentmods.dev/badge/skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer/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 pli-migration-analyzer

Your own site · 80×15
<a href="https://agentmods.dev/skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer"><img src="https://agentmods.dev/badge/skills/dauquangthanh/hanoi-rainbow/pli-migration-analyzer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 106 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,277 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00106 $0.01277
Opus 5 $0.00053 $0.00639
Sonnet 5 $0.00021 $0.00255
Haiku 4.5 $0.00011 $0.00128

Measured 11d ago against content hash fa9d65730940, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pli-migration-analyzer scanned grade A with 0 findings 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 11d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/analyze-dependencies.ps1, scripts/analyze-dependencies.sh, scripts/estimate-complexity.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pli-migration-analyzer/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PL/I Migration Analyzer

Analyzes legacy PL/I programs and generates Java migration strategies. Extracts business logic, data structures, procedures, and dependencies to produce actionable migration plans.

Workflow

1. Discover PL/I Programs

Find PL/I source files in the workspace:

find . -name "*.pli" -o -name "*.PLI" -o -name "*.pl1"

2. Analyze Program Structure

For each PL/I program, extract:

  • Entry points: PROCEDURE OPTIONS(MAIN)
  • Declarations: DCL statements (FIXED DECIMAL, FIXED BINARY, CHARACTER, BIT, structures)
  • Procedures: Nested procedures and functions
  • File operations: OPEN, READ, WRITE, CLOSE statements
  • Exception handling: ON conditions (ENDFILE, ERROR, etc.)
  • Dependencies: CALL statements, %INCLUDE directives

Use scripts for automation:

  • extract-structure.py <source_file> - Extract structural information
  • analyze-dependencies.sh <directory> - Generate dependency graph
  • estimate-complexity.py <source_file> - Estimate migration effort

3. Map to Java Design

Convert PL/I elements to Java:

  • Structures → POJOs with appropriate types
  • Procedures → Service methods
  • File operations → Java I/O or database operations
  • ON conditions → try-catch exception handling
  • Arrays → Lists or arrays (adjust 1-based to 0-based indexing)

Critical Type Mapping:

  • FIXED DECIMAL(n,m)BigDecimal (NEVER float/double)
  • FIXED BINARY(n)int, long
  • CHARACTER(n)String
  • BIT(1)boolean

4. Generate Java Implementation

Create Java classes using:

  • generate-java-classes.py <data_structure_file> - Generate POJOs from structures

Ensure:

  • BigDecimal for all financial calculations
  • Proper exception handling (no GO TO)
  • Array bounds adjustment (1-based → 0-based)
  • String operations adjustment (SUBSTR is 1-based, substring is 0-based)

5. Produce Migration Report

Generate comprehensive report with:

  1. Program Overview: Purpose, entry points, complexity estimate
  2. Dependencies: Called procedures, included files, external references
  3. Data Structures: Tables with PL/I types and Java equivalents
  4. Business Logic Summary: Key algorithms and rules
  5. Java Design: Proposed classes, methods, packages
  6. Migration Estimate: Effort in person-days, risk assessment
  7. Action Items: Prioritized tasks with owners

Read the full file on GitHub · 172 lines

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. 11d ago First seen · 172 lines · 106 tokens per session scan A fa9d65730940

Subscribe to this mod's changes

pli-migration-analyzer is a skill published in the GitHub repository DauQuangThanh/hanoi-rainbow (16 stars, last pushed 7mo ago), licensed MIT. It adds 106 tokens to every session and 1,277 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.