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/adambien/airails/concept-extractornpx skills add AdamBien/airails --skill concept-extractorgit clone --depth 1 https://github.com/AdamBien/airailsWrote 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.
[](https://agentmods.dev/skills/adambien/airails/concept-extractor)<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>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 | $0.00144 | $0.01283 |
| Opus 5 | $0.00072 | $0.00642 |
| Sonnet 5 | $0.00029 | $0.00257 |
| Haiku 4.5 | $0.00014 | $0.00128 |
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.
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
- Inventory which naming sources exist in the system (see ranking below).
- Mine every source. Tokenize compound names:
CustomerContractValidationServiceFactoryImpl→ Customer, Contract, Validation. - Strip pattern noise using references/noise-words.md. Keep the discards for the noise report.
- Cluster aliases into one concept per meaning (Customer / Client / Kunde /
CUST). Expand abbreviations from surrounding context — column names, labels, Javadoc. - Record co-occurrence: two concepts co-occur when they share a class, table, URL path, or UI view.
- Write
migration/CONCEPTS.mdin the analyzed project — all pipeline artifacts live in this folder, never at the legacy project's root. - Seed
migration/GLOSSARY.mdif 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:
- Database schema — tables, columns, constraints. Survived every refactoring fashion; usually the most honest source.
- UI labels — JSP/JSF/HTML text, i18n bundles, report headers. Closest to the language the business actually speaks.
- External contracts — REST/URL paths, queue and topic names, WSDL, exchanged file names.
- Configuration keys, enum values, exception names.
- Code identifiers — packages, classes, methods, fields. Most numerous, least reliable.
- 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>
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.
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.
- 5d ago First seen · 86 lines · 144 tokens per session scan A 027f691a0fe6
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.
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…
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…
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…
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.
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.
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.