What is run-analysis?

A guide for operating a tool that reverse-engineers COBOL source code, meaning it examines older programs to explain their structure and behaviour. It covers creating a workspace, splitting large programs into chunks, and running analysis.

Use it to initialise a workspace, stage large programs, analyse one program or all programs, and choose analysis strategies or workers.

It provides the required setup, commands, options, and prerequisites needed to analyse COBOL reliably.

How dsheard/cobol-o-matic configures Claude Code

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/skills/run-analysis/SKILL.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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dsheard/cobol-o-matic/run-analysis/github.svg)](https://agentmods.dev/skills/dsheard/cobol-o-matic/run-analysis)

Your own site

<a href="https://agentmods.dev/skills/dsheard/cobol-o-matic/run-analysis"><img src="https://agentmods.dev/badge/skills/dsheard/cobol-o-matic/run-analysis/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dsheard/cobol-o-matic/run-analysis"><img src="https://agentmods.dev/badge/skills/dsheard/cobol-o-matic/run-analysis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,407 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.

Model	Per session	Once invoked
Fable 5.1	$0.00051	$0.01407
Opus 5	$0.00026	$0.00704
Sonnet 5	$0.00010	$0.00281
Haiku 4.5	$0.00005	$0.00141

Measured 9d ago against content hash 5afe7fdf605a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

run-analysis 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/skills/run-analysis/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Running the Analysis Tool

Prerequisites

Python 3.10+
pip install -r requirements.txt (claude-agent-sdk, pyyaml, python-dotenv)
ANTHROPIC_API_KEY env var (direct API) or ANTHROPIC_BASE_URL + ANTHROPIC_API_KEY (AI gateway)

Commands

init -- Scaffold a Workspace

python analyse.py init
python analyse.py init --workspace /path/to/workspace

Creates workspace/ with config.yaml, CLAUDE.md, source/, output/ subdirectories. After init, edit config.yaml to point at your COBOL source files.

stage -- Pre-chunk Large Programs

python analyse.py stage                          # stage all programs
python analyse.py stage --program COACTUPC       # stage one program
python analyse.py stage --chunk-threshold 600    # override line threshold

Deterministically splits programs exceeding chunk_threshold lines into paragraph-grouped chunks in staging/. The run command auto-stages, so explicit staging is only needed for inspection or custom thresholds.

run -- Execute Analysis

python analyse.py run                            # auto-strategy (recommended)
python analyse.py run --program ACCT0100         # single program
python analyse.py run --workers inventory,flow   # specific workers only
python analyse.py run --dry-run                  # report without writing files
python analyse.py run --resume                   # continue a failed run
python analyse.py run --verbose                  # debug logging
python analyse.py run --workspace /path/to/ws    # explicit workspace path

Run Strategies

The strategy setting in config.yaml (or auto-detected) controls the workflow:

Programs	Auto Strategy	Behaviour
1-10	`default`	All workers in a single session, multi-iteration convergence
11+	`phased`	Phase 1-5: cross-cutting -> per-program sweep -> synthesis -> tests -> impl plan

Read the full file on GitHub · 143 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.

9d ago First seen · 143 lines · 51 tokens per session scan A 5afe7fdf605a

Subscribe to this mod's changes

run-analysis is a skill published in the GitHub repository dsheard/cobol-o-matic (5 stars, last pushed 5mo ago), licensed MIT. It adds 51 tokens to every session and 1,407 once invoked, about $0.0003 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.

Research ai-agents claude cobol legacy-modernization mainframe requirements-extraction

ile-cobol-docs

IBM ILE COBOL 7.4/7.5 — language structure, four divisions, data description, file handling, DB2, debugging.

pledgeandgrow/pledge-skills · 38 tokens

mk:confluence-spec-analyst

Deep spec analysis on a Confluence page. Reads page (+ children) via the confluence-as wrapper, produces a structured Spec Research Report with requirements, acceptance criteria, gaps, ambiguities, and suggested user stories for human review. Read-only — does NOT create Jira tickets. Triggers: 'analyze spec for…

ngocsangyem/MeowKit · 112 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

cobol-o-matic: Skill for Claude Code