concept-extractor

concept-extractor is a skill for Claude Code, Codex from AdamBien/airails. It costs 144 tokens per session (1,283 once invoked), scanned A, original, MIT.

A method for recovering business terms from an older software system by examining names in its database, screens, URLs, settings, code, and documentation. It records possible concepts, alternate names, and where they appear.

In plain words
What is it for?
Use it to create a reviewable CONCEPTS.md and propose entries for GLOSSARY.md before planning a system migration.
Why use it?
Older systems often hide their real business meaning behind technical structure, making migrations and redesigns harder to understand.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/adambien/airails/concept-extractor
Any agent
npx skills add AdamBien/airails --skill concept-extractor
Clone the repo
git clone --depth 1 https://github.com/AdamBien/airails

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 concept-extractor

README.md
[![agentmods](https://agentmods.dev/badge/skills/adambien/airails/concept-extractor.svg)](https://agentmods.dev/skills/adambien/airails/concept-extractor)
Your own site
<a href="https://agentmods.dev/skills/adambien/airails/concept-extractor"><img src="https://agentmods.dev/badge/skills/adambien/airails/concept-extractor.svg" alt="Measured on agentmods" height="20"></a>
Per session 144 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,283 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00144 $0.01283
Opus 5 $0.00072 $0.00642
Sonnet 5 $0.00029 $0.00257
Haiku 4.5 $0.00014 $0.00128

Measured 5d ago against content hash 027f691a0fe6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

concept-extractor 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 5d 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.

migrations/concept-extractor/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Concept Extractor

Recover the domain language buried in a legacy system's names. The technical structure of overengineered systems lies about the domain — packages reflect patterns, not business capabilities. Names are where the original domain knowledge survived. Produce candidates for human review, never verdicts.

Workflow

  1. Inventory which naming sources exist in the system (see ranking below).
  2. Mine every source. Tokenize compound names: CustomerContractValidationServiceFactoryImpl → Customer, Contract, Validation.
  3. Strip pattern noise using references/noise-words.md. Keep the discards for the noise report.
  4. Cluster aliases into one concept per meaning (Customer / Client / Kunde / CUST). Expand abbreviations from surrounding context — column names, labels, Javadoc.
  5. Record co-occurrence: two concepts co-occur when they share a class, table, URL path, or UI view.
  6. Write migration/CONCEPTS.md in the analyzed project — all pipeline artifacts live in this folder, never at the legacy project's root.
  7. Seed migration/GLOSSARY.md if absent. If present, append proposals under ## Proposed — never modify existing entries.

Naming Sources — Ranked by Trustworthiness

Mine all that exist. When sources conflict, trust the higher-ranked one:

  1. Database schema — tables, columns, constraints. Survived every refactoring fashion; usually the most honest source.
  2. UI labels — JSP/JSF/HTML text, i18n bundles, report headers. Closest to the language the business actually speaks.
  3. External contracts — REST/URL paths, queue and topic names, WSDL, exchanged file names.
  4. Configuration keys, enum values, exception names.
  5. Code identifiers — packages, classes, methods, fields. Most numerous, least reliable.
  6. Comments, Javadoc, test names, documentation.

CONCEPTS.md Format

Regenerable, evidence-oriented, diffable. Use this structure:

# Concepts: <system name>

## Concepts
### <Concept>
- **Aliases:** <all forms found, incl. abbreviations>
- **Sources:** DB / UI / contracts / code — with concrete pointers (table, file, path)
- **Frequency:** <n> | **Confidence:** high | medium | low
- **Co-occurs with:** <Concept> (<count>), ...

## Co-occurrence
<table or Mermaid graph of concept pairs with counts>

## Noise Report
<stripped words with counts — makes the extraction auditable>

## Open Questions
### Q<n> — <one-line question>
<evidence pointers; candidate answers when enumerable — suspected synonyms
across sources, homonyms in different contexts (often the first hint of a
BC boundary), unexpandable abbreviations>

Read the full file on GitHub · 86 lines

Files

What ships with it

2 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. 5d ago First seen · 86 lines · 144 tokens per session scan A 027f691a0fe6

Subscribe to this mod's changes

concept-extractor is a skill published in the GitHub repository AdamBien/airails (48 stars, last pushed 15d ago), licensed MIT. It adds 144 tokens to every session and 1,283 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

js-gof

Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…

metarhia/metaskills · 107 tokens

data-structures

Implements custom JavaScript data structures: queues, deques, stacks, linked lists, cons lists, circular buffers, unrolled lists, tries, heaps, graphs, LRU caches, CRDTs, pools, structs. Use when building or choosing non-native collections, optimizing enqueue/dequeue, designing persistent lists, or when the user asks…

metarhia/metaskills · 84 tokens

js-data-structures

Choose and use native JavaScript collections for Big-O, readability, semantics, naming, stability, or testability. Use when working with Map, Object, Set, Array, WeakMap, WeakSet, TypedArray, or deciding among built-in collections. For custom queues, lists, heaps, tries, and related structures, use the data-structures…

metarhia/metaskills · 77 tokens

metautil-data-structures

Operate metautil package ADTs — ConsList, Struct, Queue, Stack, Deque, List, Trie, UnrolledList, CircularBuffer. Use when importing or calling these classes from metautil. For native Map/Object/Set/Array, use js-data-structures. For custom data structures, use data-structures.

metarhia/metaskills · 75 tokens

npm-publish

Prepare an npm package for publishing. Handles version bump, CHANGELOG update, typings check, test run, README refresh, package.json audit, and npm pack verification. Use when the user asks to prepare a release, bump version, publish a package, or do release prep.

metarhia/metaskills · 59 tokens

error-handling

Apply error handling and recovery patterns in JavaScript/TypeScript or Node.js. Use when implementing error handling, retry logic, or when the user mentions domain errors, error recovery, error escalation.

metarhia/metaskills · 43 tokens