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.
npx agentmods add skills/openhands/extensions/cobol-modernizationnpx skills add OpenHands/extensions --skill cobol-modernizationgit clone --depth 1 https://github.com/OpenHands/extensionsWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00032 | $0.00879 |
| Opus 5 | $0.00016 | $0.00439 |
| Sonnet 5 | $0.00006 | $0.00176 |
| Haiku 4.5 | $0.00003 | $0.00088 |
Grade A, and why
cobol-modernization 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 2d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
End-to-end workflow for migrating COBOL codebases to Java.
Overview
This plugin orchestrates a multi-phase COBOL modernization project:
- Build Setup — Configure compilation for both COBOL and Java, create test fixtures
- Mainframe Planning — Document transformations needed to remove mainframe dependencies
- Mainframe Removal — Convert CICS/VSAM code to standard COBOL
- Java Migration — Translate standardized COBOL to idiomatic Java
Prerequisites
- GnuCOBOL compiler (
cobc) - Java 11+ with Maven or Gradle
- Python 3.13 with
uv - LLM API key (Anthropic or OpenAI)
Quick Start
export LLM_API_KEY="your-api-key"
export LLM_MODEL="anthropic/claude-3-5-sonnet-20241022"
uv run python -m lc_sdk_examples.cobol_modernization --src-path /path/to/cobol/project
PowerShell equivalent for the environment setup:
$env:LLM_API_KEY = "your-api-key"
$env:LLM_MODEL = "anthropic/claude-3-5-sonnet-20241022"
uv run python -m lc_sdk_examples.cobol_modernization --src-path C:\path\to\cobol\project
Workflow Phases
Phase 1: Build Setup
Creates the foundation for the migration:
- COBOL compilation environment (GnuCOBOL)
- Java project structure (Maven/Gradle + JUnit 5)
- Test fixtures with golden outputs from COBOL execution
Outputs:
build_notes.md— Build instructionstest-fixtures/— Input/output test datatest_manifest.json— Test case mapping
Phase 2: Mainframe Planning
See ../mainframe-planning/SKILL.md
Creates a transformation guide without modifying code:
- Maps CICS/VSAM constructs to standard COBOL equivalents
- Documents error handling replacements
- Identifies UI operations to stub
Output:
mainframe_dependency_removal_plan.md
Phase 3: Mainframe Removal
See ../mainframe-removal/SKILL.md
Applies the transformation guide:
- Replaces EXEC CICS commands with file I/O
- Adds FILE STATUS checking
- Stubs BMS/screen operations
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.
- 2d ago First seen · 123 lines · 32 tokens per session scan A 551452a76770
cobol-modernization is a skill published in the GitHub repository OpenHands/extensions (137 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 879 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
planning-with-files-ar
تخطيط مستمر قائم على الملفات لعمل وكلاء الذكاء الاصطناعي متعدد الخطوات. يحتفظ بملفات taskplan.md و findings.md و progress.md على القرص، وتحقن خطافات دورة الحياة سياق التخطيط المحدد للمشروع. تقرأ الاستعادة التلقائية ملفات تخطيط المشروع فقط. يمكن للأمر الصريح session-catchup.py --metadata فحص بيانات وصفية لجلسات الوكيل…
kl-consistency-test
Write, calibrate, and debug the prefill-vs-decode logprob (KL) consistency tests in sglang -- the two independent conditions a zero requires (every operator batch-invariant, and the two paths computing the same function), which helper separates them, how to pick a threshold once they hold, and how to localize a…
i18n-localization
Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.
dsh-web-documentation
Use when adding or editing dsh-web README files, docs, AGENTS.md instructions, user-facing configuration text, or bilingual documentation pairs.
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
indication-dossier
Build a source-backed biomedical indication dossier. Use when a research task asks for disease biology, target rationale, patient segmentation, biomarkers, trials, drugs, competitive landscape, or translational evidence.