cobol-o-matic: Instructions file for Claude Code

CLAUDE.md

cobol-o-matic CLAUDE.md is an instructions file for Claude Code from dsheard/cobol-o-matic. It costs 1,998 tokens per session, scanned A, original, MIT.

A guide for a tool that examines COBOL applications and turns their structure into organized Markdown documents. COBOL is a programming language still used in many older business systems.

In plain words
What is it for?
Maintaining the reverse-engineering tool, its parser, staged analysis process, saved state, validation, logging, and specialist agents.
Why use it?
It helps developers understand unfamiliar COBOL code without manually tracing the whole application.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents.

This is dsheard/cobol-o-matic's own configuration. It tells Claude Code how to work on cobol-o-matic itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cobol-o-matic configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dsheard/cobol-o-matic. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/dsheard/cobol-o-matic/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/dsheard/cobol-o-matic

Made for: Claude Code.

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 cobol-o-matic CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dsheard/cobol-o-matic/claude-md/github.svg)](https://agentmods.dev/instructions/dsheard/cobol-o-matic/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/dsheard/cobol-o-matic/claude-md"><img src="https://agentmods.dev/badge/instructions/dsheard/cobol-o-matic/claude-md/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 cobol-o-matic CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/dsheard/cobol-o-matic/claude-md"><img src="https://agentmods.dev/badge/instructions/dsheard/cobol-o-matic/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,998 This file is loaded in full into every session.
When invoked 1,998 The same file — it is already loaded in full.
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 $0.01998 $0.01998
Opus 5 $0.00999 $0.00999
Sonnet 5 $0.00400 $0.00400
Haiku 4.5 $0.00200 $0.00200

Measured 9d ago against content hash 9b3948aaf7c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

cobol-o-matic CLAUDE.md 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 9d 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.

CLAUDE.md · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

COBOL Reverse Engineering Tool

An agentic tool that reverse-engineers COBOL applications into structured markdown artifacts. Uses the Claude Agent SDK to spawn specialised subagents.

Directory Layout

analyse.py       # Thin CLI entry point
orchestrator/                   # Core Python package
├── __init__.py                 #   Shared constants and utilities
├── models.py                   #   Dataclasses (Discovery, Paragraph, Chunk, Manifest)
├── state.py                    #   State persistence and convergence tracking
├── parser.py                   #   Deterministic COBOL structural parser
├── stager.py                   #   Chunk staging pipeline
├── validator.py                #   Deterministic artifact validation
├── tracing.py                  #   JSONL event logging and optional OTEL tracing
├── config.py                   #   Config loading, defaults, workspace scaffolding
├── agents.py                   #   Agent construction, SDK interaction, critic
├── runner.py                   #   Run strategies, phased execution, sweep
└── cli.py                      #   CLI argument parsing, command handlers, main()
prompts/                        # Agent prompt builders (one per worker)
├── _helpers.py                 #   Shared helpers (_source_context, _read_template, etc.)
├── inventory.py                #   Inventory worker prompt
├── data.py                     #   Data worker prompt
├── business_rules.py           #   Business rules worker prompt (+ chunked variant)
├── flow.py                     #   Flow worker prompt
├── integration.py              #   Integration worker prompt
├── requirements.py             #   Requirements-deriver prompt
├── test_specs.py               #   Test-specs-deriver prompt
├── implementation.py           #   Implementation-plan-deriver prompt
├── critic.py                   #   LLM critic prompt for corrective passes
└── orchestrator.py             #   Orchestrator prompt and helpers
templates/                      # Output artifact templates (frontmatter schema + sections)
examples/                       # Reference configs for open-source COBOL apps
workspace/                      # Analysis workspace (agents run here)
├── config.yaml                 #   Config: source paths, output dir, settings
├── CLAUDE.md                   #   Agent-focused output conventions
├── source/                     #   COBOL input files
├── output/                     #   Generated markdown artifacts
├── staging/                    #   Chunked files for large programs
├── state/                      #   Run state JSON files (convergence tracking)
└── logs/                       #   JSONL event logs and agent transcripts

Read the full file on GitHub · 164 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. 9d ago First seen · 164 lines · 1,998 tokens per session scan A 9b3948aaf7c0

Subscribe to this mod's changes

cobol-o-matic CLAUDE.md is an instructions file published in the GitHub repository dsheard/cobol-o-matic (5 stars, last pushed 5mo ago), licensed MIT. It adds 1,998 tokens to every session, about $0.0100 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 instructions, from other repositories

agent-ready copilot-instructions.md

Instructions for vb-nattamai/agent-ready, covering copilot instructions — helloworld, project summary, commands, module layout and restricted paths.

vb-nattamai/agent-ready · 578 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens