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 skills add TypeFox/agent-skills --skill domainmodel-dsl-v2git clone --depth 1 https://github.com/TypeFox/agent-skillsWrote 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/typefox/agent-skills/domainmodel-dsl-v2)<a href="https://agentmods.dev/skills/typefox/agent-skills/domainmodel-dsl-v2"><img src="https://agentmods.dev/badge/skills/typefox/agent-skills/domainmodel-dsl-v2/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.
<a href="https://agentmods.dev/skills/typefox/agent-skills/domainmodel-dsl-v2"><img src="https://agentmods.dev/badge/skills/typefox/agent-skills/domainmodel-dsl-v2.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.00841 |
| Opus 5.5 | $0.00027 | $0.00336 |
| Sonnet 5.5 | $0.00014 | $0.00168 |
| Haiku 4.5 | $0.00007 | $0.00084 |
Grade A, and why
domainmodel-dsl 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 1mo 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Domain Model DSL
A language for describing a data model: primitive datatypes, entities with features,
inheritance between entities, and packages that namespace declarations. A .dmodel file is a
flat sequence of top-level elements (packages or types); there is no module header.
Top-level structure
A file is zero or more elements, each either a package or a type (a datatype or an entity):
datatype String
datatype Int
entity Person {
name: String
}
Syntax (EBNF)
domainmodel_file = { top_level_element } ;
top_level_element = package | type ;
package = "package", qualified_name, "{", { top_level_element }, "}" ;
type = datatype | entity ;
datatype = "datatype", identifier ;
entity = "entity", identifier, [ extends_clause ], "{", { feature }, "}" ;
extends_clause = "extends", qualified_name ;
feature = [ "many" ], identifier, ":", qualified_name ;
qualified_name = identifier, { ".", identifier } ;
identifier = letter, { letter | digit | "_" } ;
letter = "A" | "B" | ... | "Z" | "a" | "b" | ... | "z" ;
Datatypes
A primitive type:
datatype String
Entities, features, inheritance
An entity has a name, an optional supertype, and a block of features:
entity Person {
name: String
age: Int
}
entity Employee extends Person {
salary: Int
}
extends <Entity>— single inheritance; the supertype is referenced by its (qualified) name and must resolve to an entity.- Each feature is
(<many>)? <name> : <Type>. The type is a datatype or an entity, referenced by its (qualified) name. - Prefix a feature with
manyto make it multi-valued (a collection):
entity Blog {
title: String
many posts: Post
}
Packages and qualified names
package <QualifiedName> { ... } groups elements and can nest. A qualified name is one or
more identifiers joined by dots (foo.bar.Baz). References use qualified names to reach
declarations in other packages; from inside a package you may use a name relative to the current
scope:
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.
- 1mo ago First seen · 145 lines · 68 tokens per session scan A ec19f2a08706
domainmodel-dsl is a skill published in the GitHub repository TypeFox/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 841 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
loom-database-design
Database schema and data model design for relational, NoSQL, time-series, and warehouse systems. Not for: event messaging.
loom-sql-optimization
Analyzes and optimizes SQL queries for performance.
loom-caching
Caching strategies for performance optimization — cache-aside, write-through, write-behind, TTL policies, eviction, and stampede prevention.
loom-search
Full-text search and search engine implementation. Not for: an auth/JWT token or an LLM context token.
Agent Design Principles
A checklist for designing agent personas, skills, and multi-agent pipelines that stay reliable as they grow — grounded in the 12-factor-agents principles.
Migration Safety
Checklist for shipping schema migrations that roll back cleanly and won't lock up a production table.