ile-cobol-docs

ile-cobol-docs is a skill for Claude Code, Codex from pledgeandgrow/pledge-skills. It costs 38 tokens per session (1,440 once invoked), scanned A, original, MIT.

Reference material for IBM ILE COBOL 7.4 and 7.5, a programming language used on IBM i business systems. It covers program structure, files, DB2 databases, debugging, and integration with the operating system.

In plain words
What is it for?
Use it when writing or understanding COBOL programs, defining data, handling files, accessing DB2, communicating between languages, or debugging IBM i applications.
Why use it?
It provides language and IBM i details that are easy to miss when working with older business software.

Skill for Claude CodeCodex

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

Good fit Use it when writing or understanding COBOL programs, defining data, handling files, accessing DB2, communicating between languages, or debugging IBM i applications.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/pledgeandgrow/pledge-skills/cobol
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 pledgeandgrow/pledge-skills --skill cobol
Clone the repo
git clone --depth 1 https://github.com/pledgeandgrow/pledge-skills

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 ile-cobol-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/cobol/github.svg)](https://agentmods.dev/skills/pledgeandgrow/pledge-skills/cobol)
Your own site
<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/cobol"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/cobol/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 ile-cobol-docs

Your own site · 80×15
<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/cobol"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/cobol.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,440 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 $0.00038 $0.01440
Opus 5 $0.00019 $0.00720
Sonnet 5 $0.00008 $0.00288
Haiku 4.5 $0.00004 $0.00144

Measured 10d ago against content hash 1fb6e386792f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ile-cobol-docs 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 10d 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.

skills/cobol/SKILL.md · 147 lines

How it starts

The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ILE COBOL Language Skill

Overview

IBM ILE COBOL (Integrated Language Environment COBOL) is a programming language available on IBM i systems. It is based on the ANSI COBOL standard with IBM extensions. ILE COBOL provides structured programming capabilities, file handling, database access, interlanguage communication, and integration with the IBM i operating system.

This skill covers IBM ILE COBOL for IBM i 7.4 (also applicable to 7.5). Source: IBM ILE COBOL Language Reference and ILE COBOL Programmer's Guide.

Key Concepts

  • COBOL Source Program: A syntactically correct set of COBOL statements organized into four divisions
  • Nesting: COBOL programs may contain other COBOL programs (nested programs); contained programs can reference resources of their containing program
  • Run Unit: A set of one or more programs functioning as a unit at run time; in ILE, composed of program objects and service programs in a single ILE activation group
  • ILE Architecture: Module creation, binding, message handling, exception handling, and debugging across multiple languages
  • Reference Format: 80-character source line with specific column areas (Sequence, Indicator, Area A, Area B, Comment)

Source Program Structure

A COBOL source program consists of four divisions, written in this order:

  1. Identification Division (required) - Names the program and provides documentary information
  2. Environment Division (optional) - Describes computer environment, files, and I/O configuration
  3. Data Division (optional) - Describes all data to be processed
  4. Procedure Division (optional) - Contains the executable logic

The end of a COBOL source program is indicated by the END PROGRAM header or by the absence of additional source lines.

Example Program

       IDENTIFICATION DIVISION.
       PROGRAM-ID.     IDSAMPLE.
       AUTHOR.         PROGRAMMER NAME.
       INSTALLATION.   COBOL DEVELOPMENT CENTER.
       DATE-WRITTEN.   12/02/94.
       DATE-COMPILED.  12/09/94 12:57:53.
       SECURITY.       NON-CONFIDENTIAL.

       ENVIRONMENT DIVISION.
       CONFIGURATION SECTION.
       SOURCE-COMPUTER. IBM-ISERIES.
       OBJECT-COMPUTER. IBM-ISERIES.
       INPUT-OUTPUT SECTION.
       FILE-CONTROL.
           SELECT FILE-1 ASSIGN TO DISK-SAMPLE.

       DATA DIVISION.
       FILE SECTION.
       FD  FILE-1
           LABEL RECORDS ARE STANDARD.
       01  RECORD-1.
           05 NAME-FIELD      PIC X(20).
           05 NO-OF-DEP       PIC 9(2).

       WORKING-STORAGE SECTION.
       01 WORK-RECORD.
           05 NAME-FIELD      PIC X(20).
           05 NO-OF-DEPENDENTS PIC 9(2).
           05 RECORD-NO       PIC 9(4).
       77 KOUNT               PIC 9(2) VALUE 0.

       PROCEDURE DIVISION.
       STEP-1.
           OPEN OUTPUT FILE-1.
           MOVE ZERO TO KOUNT.
       STEP-2.
           ADD 1 TO KOUNT.
           MOVE "SAMPLE NAME" TO NAME-FIELD.
           WRITE RECORD-1 FROM WORK-RECORD.
       STEP-3.
           CLOSE FILE-1.
           STOP RUN.

Read the full file on GitHub · 147 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 147 lines · 38 tokens per session scan A 1fb6e386792f

Subscribe to this mod's changes

ile-cobol-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,440 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 2026-08-31.

Related

Other skills, from other repositories

migrate-oxfmt

Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's formatter from Prettier or Biome to Oxfmt.

oxc-project/oxc · 53 tokens

senior-java

World-class Java and Spring Boot development skill for enterprise applications, microservices, and cloud-native systems. Expertise in Spring Framework, Spring Boot 3.x, Spring Cloud, JPA/Hibernate, and reactive programming with WebFlux. Includes project scaffolding, dependency management, security implementation, and…

benchflow-ai/skillsbench · 65 tokens

edge-python

Write, run, test and package Edge Python programs with the edge CLI. Use when editing .py files in an Edge Python project or when the user asks for Edge Python code.

dylan-sutton-chavez/edge-python · 39 tokens

java-expert

Expert-level Java development with Java 21+ features, Spring Boot, Maven/Gradle, and enterprise best practices. Use when the user mentions JVM, Spring, Maven, Gradle, or enterprise, or when the task involves Modern Java, Spring Boot, Build Tools, or Dependency Injection.

personamanagmentlayer/pcl · 63 tokens

csharp-expert

Expert-level C# development with .NET 8+, ASP.NET Core, LINQ, async/await, and enterprise patterns. Use when the user mentions C#, .NET, ASP.NET, enterprise, or Microsoft platforms, or when the task involves Modern C#, Async/Await, LINQ, or ASP.NET Core.

personamanagmentlayer/pcl · 70 tokens

axint

Use Axint MCP tools to create, compile, validate, and repair Apple App Intents and Swift surfaces from TypeScript definitions.

agenticempire/axint · 29 tokens