data-model-designer

data-model-designer is a skill for Claude Code, Codex from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction. It costs 26 tokens per session (2,290 once invoked), scanned A, original, MIT.

A data-modeling tool for construction projects. It defines the things a project tracks, how they relate, and how that information should be stored in a database.

In plain words
What is it for?
Use it to map entities and relationships, define database fields and rules, create entity-relationship diagrams, and generate database structures.
Why use it?
It reduces fragmented records, inconsistent structures, and missing links between project data. A shared model also makes information easier to combine across systems.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to map entities and relationships, define database fields and rules, create entity-relationship diagrams, and generate database structures.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer
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.

Any agent
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill data-model-designer
Clone the repo
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

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 data-model-designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer/github.svg)](https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer)
Your own site
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer/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.

agentmods 80×15 button for data-model-designer

Your own site · 80×15
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/data-model-designer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,290 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00026 $0.02290
Opus 5 $0.00013 $0.01145
Sonnet 5 $0.00005 $0.00458
Haiku 4.5 $0.00003 $0.00229

Measured 7d ago against content hash 2e1a50478481, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

data-model-designer 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 7d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

2_DDC_Book/2.5-Data-Modeling-Standards/data-model-designer/SKILL.md · 342 lines

How it starts

The opening of the file, as written. The whole thing — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Data Model Designer

Business Case

Problem Statement

Construction data management challenges:

  • Fragmented data across systems
  • Inconsistent data structures
  • Missing relationships between entities
  • Difficult data integration

Solution

Systematic data model design for construction projects, defining entities, relationships, and schemas for effective data management.

Technical Implementation

from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from enum import Enum
import json


class DataType(Enum):
    STRING = "string"
    INTEGER = "integer"
    FLOAT = "float"
    BOOLEAN = "boolean"
    DATE = "date"
    DATETIME = "datetime"
    TEXT = "text"
    JSON = "json"


class RelationType(Enum):
    ONE_TO_ONE = "1:1"
    ONE_TO_MANY = "1:N"
    MANY_TO_MANY = "N:M"


class ConstraintType(Enum):
    PRIMARY_KEY = "primary_key"
    FOREIGN_KEY = "foreign_key"
    UNIQUE = "unique"
    NOT_NULL = "not_null"


@dataclass
class Field:
    name: str
    data_type: DataType
    nullable: bool = True
    default: Any = None
    description: str = ""
    constraints: List[ConstraintType] = field(default_factory=list)


@dataclass
class Entity:
    name: str
    description: str
    fields: List[Field] = field(default_factory=list)
    primary_key: str = "id"


@dataclass
class Relationship:
    name: str
    from_entity: str
    to_entity: str
    relation_type: RelationType
    from_field: str
    to_field: str


class ConstructionDataModel:
    """Design data models for construction projects."""

    def __init__(self, project_name: str):
        self.project_name = project_name
        self.entities: Dict[str, Entity] = {}
        self.relationships: List[Relationship] = []

    def add_entity(self, entity: Entity):
        """Add entity to model."""
        self.entities[entity.name] = entity

    def add_relationship(self, relationship: Relationship):
        """Add relationship between entities."""
        self.relationships.append(relationship)

    def create_entity(self, name: str, description: str,
                      fields: List[Dict[str, Any]]) -> Entity:
        """Create entity from field definitions."""

        entity_fields = [
            Field(
                name=f['name'],
                data_type=DataType(f.get('type', 'string')),
                nullable=f.get('nullable', True),
                default=f.get('default'),
                description=f.get('description', ''),
                constraints=[ConstraintType(c) for c in f.get('constraints', [])]
            )
            for f in fields
        ]

        entity = Entity(name=name, description=description, fields=entity_fields)
        self.add_entity(entity)
        return entity

    def create_relationship(self, from_entity: str, to_entity: str,
                           relation_type: str = "1:N",
                           from_field: str = None) -> Relationship:
        """Create relationship between entities."""

        rel = Relationship(
            name=f"{from_entity}_{to_entity}",
            from_entity=from_entity,
            to_entity=to_entity,
            relation_type=RelationType(relation_type),
            from_field=from_field or f"{to_entity.lower()}_id",
            to_field="id"
        )
        self.add_relationship(rel)
        return rel

    def generate_sql_schema(self, dialect: str = "postgresql") -> str:
        """Generate SQL DDL statements."""

        sql = []
        type_map = {
            DataType.STRING: "VARCHAR(255)",
            DataType.INTEGER: "INTEGER",
            DataType.FLOAT: "DECIMAL(15,2)",
            DataType.BOOLEAN: "BOOLEAN",
            DataType.DATE: "DATE",
            DataType.DATETIME: "TIMESTAMP",
            DataType.TEXT: "TEXT",
            DataType.JSON: "JSONB" if dialect == "postgresql" else "JSON"
        }

        for name, entity in self.entities.items():
            columns = []
            for fld in entity.fields:
                col = f"    {fld.name} {type_map.get(fld.data_type, 'VARCHAR(255)')}"
                if not fld.nullable:
                    col += " NOT NULL"
                if ConstraintType.PRIMARY_KEY in fld.constraints:
                    col += " PRIMARY KEY"
                columns.append(col)

            sql.append(f"CREATE TABLE {name} (\n" + ",\n".join(columns) + "\n);")

        for rel in self.relationships:
            sql.append(f"""ALTER TABLE {rel.from_entity}
ADD CONSTRAINT fk_{rel.name}
FOREIGN KEY ({rel.from_field}) REFERENCES {rel.to_entity}({rel.to_field});""")

        return "\n\n".join(sql)

    def generate_json_schema(self) -> Dict[str, Any]:
        """Generate JSON Schema representation."""

        schemas = {}
        for name, entity in self.entities.items():
            properties = {}
            required = []

            for fld in entity.fields:
                prop = {"description": fld.description}
                if fld.data_type == DataType.STRING:
                    prop["type"] = "string"
                elif fld.data_type == DataType.INTEGER:
                    prop["type"] = "integer"
                elif fld.data_type == DataType.FLOAT:
                    prop["type"] = "number"
                elif fld.data_type == DataType.BOOLEAN:
                    prop["type"] = "boolean"
                else:
                    prop["type"] = "string"

                properties[fld.name] = prop
                if not fld.nullable:
                    required.append(fld.name)

            schemas[name] = {
                "type": "object",
                "title": entity.description,
                "properties": properties,
                "required": required
            }
        return schemas

    def generate_er_diagram(self) -> str:
        """Generate Mermaid ER diagram."""

        lines = ["erDiagram"]
        for name, entity in self.entities.items():
            for fld in entity.fields[:5]:
                lines.append(f"    {name} {{")
                lines.append(f"        {fld.data_type.value} {fld.name}")
                lines.append("    }")

        for rel in self.relationships:
            rel_symbol = {
                RelationType.ONE_TO_ONE: "||--||",
                RelationType.ONE_TO_MANY: "||--o{",
                RelationType.MANY_TO_MANY: "}o--o{"
            }.get(rel.relation_type, "||--o{")
            lines.append(f"    {rel.from_entity} {rel_symbol} {rel.to_entity} : \"{rel.name}\"")

        return "\n".join(lines)

    def validate_model(self) -> List[str]:
        """Validate data model for issues."""

        issues = []
        for rel in self.relationships:
            if rel.from_entity not in self.entities:
                issues.append(f"Missing entity: {rel.from_entity}")
            if rel.to_entity not in self.entities:
                issues.append(f"Missing entity: {rel.to_entity}")

        for name, entity in self.entities.items():
            has_pk = any(ConstraintType.PRIMARY_KEY in f.constraints for f in entity.fields)
            if not has_pk:
                issues.append(f"Entity '{name}' has no primary key")

        return issues


class ConstructionEntities:
    """Standard construction data entities."""

    @staticmethod
    def project_entity() -> Entity:
        return Entity(
            name="projects",
            description="Construction projects",
            fields=[
                Field("id", DataType.INTEGER, False, constraints=[ConstraintType.PRIMARY_KEY]),
                Field("code", DataType.STRING, False, constraints=[ConstraintType.UNIQUE]),
                Field("name", DataType.STRING, False),
                Field("status", DataType.STRING),
                Field("start_date", DataType.DATE),
                Field("end_date", DataType.DATE),
                Field("budget", DataType.FLOAT)
            ]
        )

    @staticmethod
    def activity_entity() -> Entity:
        return Entity(
            name="activities",
            description="Schedule activities",
            fields=[
                Field("id", DataType.INTEGER, False, constraints=[ConstraintType.PRIMARY_KEY]),
                Field("project_id", DataType.INTEGER, False),
                Field("wbs_code", DataType.STRING),
                Field("name", DataType.STRING, False),
                Field("start_date", DataType.DATE),
                Field("end_date", DataType.DATE),
                Field("percent_complete", DataType.FLOAT)
            ]
        )

    @staticmethod
    def cost_item_entity() -> Entity:
        return Entity(
            name="cost_items",
            description="Project cost items",
            fields=[
                Field("id", DataType.INTEGER, False, constraints=[ConstraintType.PRIMARY_KEY]),
                Field("project_id", DataType.INTEGER, False),
                Field("wbs_code", DataType.STRING),
                Field("description", DataType.STRING),
                Field("budgeted_cost", DataType.FLOAT),
                Field("actual_cost", DataType.FLOAT)
            ]
        )

Read the full file on GitHub · 342 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. 7d ago First seen · 342 lines · 26 tokens per session scan A 2e1a50478481

Subscribe to this mod's changes

data-model-designer is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (308 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 2,290 once invoked, about $0.0001 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 2026-09-03.