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/enterprisifiernpx skills add AdamBien/airails --skill enterprisifiergit 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/enterprisifier)<a href="https://agentmods.dev/skills/adambien/airails/enterprisifier"><img src="https://agentmods.dev/badge/skills/adambien/airails/enterprisifier.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 | $0.00131 | $0.02446 |
| Opus 5 | $0.00066 | $0.01223 |
| Sonnet 5 | $0.00026 | $0.00489 |
| Haiku 4.5 | $0.00013 | $0.00245 |
Grade A, and why
enterprisifier 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overengineering
Transform any simple, working code into a maximally abstracted, pattern-saturated, enterprise-grade architecture. No line of implementation shall be directly reachable. Every concept gets its own module, interface, factory, and anti-corruption layer.
Philosophy
- Never depend on implementation — all access goes through at least 3 layers of abstraction
- Every pattern is applicable — if a GoF pattern exists, use it, even if it adds no value
- More modules = more enterprise — a single class is a failure; a 47-class hierarchy is a feature
- Abstractions over results — the code doesn't need to be faster, just more abstract
- Future-proof everything — defend against requirements that will never come
Mandatory Patterns to Apply
Apply ALL of the following to every piece of code, regardless of size or complexity:
Structural Patterns (apply all)
- Facade — wrap every public API in a facade
- Proxy — add a proxy in front of every facade
- Decorator — wrap every proxy in a decorator for cross-cutting concerns
- Adapter — adapt every external type into an internal type
- Bridge — separate every abstraction from its implementation
- Composite — model everything as a tree, even single values
- Flyweight — pool and share objects even when memory is not a concern
Creational Patterns (apply all)
- Abstract Factory — never use
newdirectly; always go through a factory of factories - Builder — every object with more than zero fields gets a builder
- Singleton — critical services are singletons, accessed through a registry
- Prototype — support cloning on every entity, just in case
- Factory Method — subclasses decide which class to instantiate
Behavioral Patterns (apply all)
- Strategy — every
ifstatement becomes a strategy interface with injectable implementations - Observer — every state change fires events through an event bus
- Command — every method call becomes a command object with undo support
- Chain of Responsibility — every request passes through a chain of handlers
- Mediator — components never talk directly; everything goes through a mediator
- Memento — every object supports full state snapshots and rollback
- State — every status field becomes a state machine with dedicated state classes
- Template Method — every algorithm is a skeleton with overridable hook methods
- Visitor — every operation on a structure is a separate visitor
- Iterator — custom iterators for every collection, never use built-in for-each
- Interpreter — configuration is a DSL parsed by an interpreter
What ships with it
1 file 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 · 203 lines · 131 tokens per session scan A 3246f96a83ae
enterprisifier is a skill published in the GitHub repository AdamBien/airails (48 stars, last pushed 15d ago), licensed MIT. It adds 131 tokens to every session and 2,446 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
deno-sandbox
Use when building features that execute untrusted user code, AI-generated code, or need isolated code execution environments. Covers the @deno/sandbox SDK.
deno-frontend
Use when building a web frontend with Deno — running React, Vite, Astro, SvelteKit, Next.js, Nuxt or other npm frameworks under Deno, or working with Fresh, Deno's own island-architecture framework. Covers which path to pick, Fresh 2.x routes, handlers, islands, Preact signals, Tailwind, and Fresh 1.x to 2.x migration.
5writing
数学建模竞赛论文撰写阶段,支持 Typst 和 LaTeX 双引擎。根据 ANALYSISMODELINGREPORT.md、RESULTSREPORT.md 和 figures/.pdf 选择比赛模板、排版引擎、组织章节,并在论文正文中按章节直接插入图表。.
6verity
数学建模竞赛最终验证和验收阶段,支持 Typst 和 LaTeX 双引擎。用于论文写完后检查章节数量、标题顺序、图表引用、数值一致性、占位符、内部文件泄露、参考文献、代码可复现性、编译和提交就绪状态。.
typst-author
Generate idiomatic Typst (.typ) code, edit and troubleshoot Typst documents and projects, and answer Typst syntax/reference questions. Use when working with .typ files or when the user explicitly asks for Typst document creation, editing, debugging, compilation, formatting, template work, or package usage.
1start-mathmodel
数学建模竞赛工作流入口。用于启动完整建模流程:询问用户偏好,生成 plan.md 和 todo.md,并按阶段调用赛题分析、建模、代码与图表、流程图、论文撰写、验证验收等 skills。.