Cwicr Cost Calculator logo

Cwicr Cost Calculator

Community
datadrivenconstruction
cwicr-cost-calculator

Calculate construction costs using DDC CWICR resource-based methodology. Break down costs into labor, materials, equipment with transparent pricing.

Overview

Publisherdatadrivenconstruction
RepositoryDDC_Skills_for_AI_Agents_in_Construction
Skill namecwicr-cost-calculator
Stars
365
Forks
91
Bundled files
2
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by datadrivenconstruction on GitHub. Read the source before you install it.

Installation

Install the Cwicr Cost Calculator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/main/1_DDC_Toolkit/CWICR-Database/cwicr-cost-calculator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction.git /tmp/DDC_Skills_for_AI_Agents_in_Construction
mkdir -p .claude/skills
cp -r /tmp/DDC_Skills_for_AI_Agents_in_Construction/1_DDC_Toolkit/CWICR-Database/cwicr-cost-calculator .claude/skills/cwicr-cost-calculator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cwicr Cost Calculator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cwicr Cost Calculator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cwicr Cost Calculator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

CWICR Cost Calculator

Business Case

Problem Statement

Traditional cost estimation often produces "black box" estimates with hidden markups. Stakeholders need:

  • Transparent cost breakdowns
  • Traceable pricing logic
  • Auditable calculations
  • Resource-level detail

Solution

Resource-based cost calculation using CWICR methodology that separates physical norms (labor hours, material quantities) from volatile prices, enabling transparent and auditable estimates.

Business Value

  • Full transparency - Every cost component visible
  • Auditable - Traceable calculation logic
  • Flexible - Update prices without changing norms
  • Accurate - Based on 55,000+ validated work items

Technical Implementation

Prerequisites

bash
pip install pandas numpy

Python Implementation

python
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from enum import Enum
from datetime import datetime


class CostComponent(Enum):
    """Cost breakdown components."""
    LABOR = "labor"
    MATERIAL = "material"
    EQUIPMENT = "equipment"
    OVERHEAD = "overhead"
    PROFIT = "profit"
    TOTAL = "total"


class CostStatus(Enum):
    """Cost calculation status."""
    CALCULATED = "calculated"
    ESTIMATED = "estimated"
    MISSING_DATA = "missing_data"
    ERROR = "error"


@dataclass
class CostBreakdown:
    """Detailed cost breakdown for a work item."""
    work_item_code: str
    description: str
    unit: str
    quantity: float

    labor_cost: float = 0.0
    material_cost: float = 0.0
    equipment_cost: float = 0.0
    overhead_cost: float = 0.0
    profit_cost: float = 0.0

    unit_price: float = 0.0
    total_cost: float = 0.0

    labor_hours: float = 0.0
    labor_rate: float = 0.0

    resources: List[Dict[str, Any]] = field(default_factory=list)
    status: CostStatus = CostStatus.CALCULATED

    def to_dict(self) -> Dict[str, Any]:
        return {
            'work_item_code': self.work_item_code,
            'description': self.description,
            'unit': self.unit,
            'quantity': self.quantity,
            'labor_cost': self.labor_cost,
            'material_cost': self.material_cost,
            'equipment_cost': self.equipment_cost,
            'overhead_cost': self.overhead_cost,
            'profit_cost': self.profit_cost,
            'total_cost': self.total_cost,
            'status': self.status.value
        }


@dataclass
class CostSummary:
    """Summary of cost estimate."""
    total_cost: float
    labor_total: float
    material_total: float
    equipment_total: float
    overhead_total: float
    profit_total: float

    item_count: int
    currency: str
    calculated_at: datetime

    breakdown_by_category: Dict[str, float] = field(default_factory=dict)


class CWICRCostCalculator:
    """Resource-based cost calculator using CWICR methodology."""

    DEFAULT_OVERHEAD_RATE = 0.15  # 15% overhead
    DEFAULT_PROFIT_RATE = 0.10   # 10% profit

    def __init__(self, cwicr_data: pd.DataFrame,
                 overhead_rate: float = None,
                 profit_rate: float = None,
                 currency: str = "USD"):
        """Initialize calculator with CWICR data."""
        self.data = cwicr_data
        self.overhead_rate = overhead_rate or self.DEFAULT_OVERHEAD_RATE
        self.profit_rate = profit_rate or self.DEFAULT_PROFIT_RATE
        self.currency = currency

        # Index data for fast lookup
        self._index_data()

    def _index_data(self):
        """Create index for fast work item lookup."""
        if 'work_item_code' in self.data.columns:
            self._code_index = self.data.set_index('work_item_code')
        else:
            self._code_index = None

    def calculate_item_cost(self, work_item_code: str,
                            quantity: float,
                            price_overrides: Dict[str, float] = None) -> CostBreakdown:
        """Calculate cost for single work item."""

        # Find work item in database
        if self._code_index is not None and work_item_code in self._code_index.index:
            item = self._code_index.loc[work_item_code]
        else:
            # Try partial match
            matches = self.data[
                self.data['work_item_code'].str.contains(work_item_code, case=False, na=False)
            ]
            if matches.empty:
                return CostBreakdown(
                    work_item_code=work_item_code,
                    description="NOT FOUND",
                    unit="",
                    quantity=quantity,
                    status=CostStatus.MISSING_DATA
                )
            item = matches.iloc[0]

        # Get base costs
        labor_unit = float(item.get('labor_cost', 0) or 0)
        material_unit = float(item.get('material_cost', 0) or 0)
        equipment_unit = float(item.get('equipment_cost', 0) or 0)

        # Apply price overrides if provided
        if price_overrides:
            if 'labor_rate' in price_overrides:
                labor_norm = float(item.get('labor_norm', 0) or 0)
                labor_unit = labor_norm * price_overrides['labor_rate']
            if 'material_factor' in price_overrides:
                material_unit *= price_overrides['material_factor']
            if 'equipment_factor' in price_overrides:
                equipment_unit *= price_overrides['equipment_factor']

        # Calculate component costs
        labor_cost = labor_unit * quantity
        material_cost = material_unit * quantity
        equipment_cost = equipment_unit * quantity

        # Direct costs
        direct_cost = labor_cost + material_cost + equipment_cost

        # Overhead and profit
        overhead_cost = direct_cost * self.overhead_rate
        profit_cost = (direct_cost + overhead_cost) * self.profit_rate

        # Total
        total_cost = direct_cost + overhead_cost + profit_cost

        # Unit price
        unit_price = total_cost / quantity if quantity > 0 else 0

        return CostBreakdown(
            work_item_code=work_item_code,
            description=str(item.get('description', '')),
            unit=str(item.get('unit', '')),
            quantity=quantity,
            labor_cost=labor_cost,
            material_cost=material_cost,
            equipment_cost=equipment_cost,
            overhead_cost=overhead_cost,
            profit_cost=profit_cost,
            unit_price=unit_price,
            total_cost=total_cost,
            labor_hours=float(item.get('labor_norm', 0) or 0) * quantity,
            labor_rate=float(item.get('labor_rate', 0) or 0),
            status=CostStatus.CALCULATED
        )

    def calculate_estimate(self, items: List[Dict[str, Any]],
                          group_by_category: bool = True) -> CostSummary:
        """Calculate cost estimate for multiple items."""

        breakdowns = []
        for item in items:
            code = item.get('work_item_code') or item.get('code')
            qty = item.get('quantity', 0)
            overrides = item.get('price_overrides')

            breakdown = self.calculate_item_cost(code, qty, overrides)
            breakdowns.append(breakdown)

        # Aggregate totals
        labor_total = sum(b.labor_cost for b in breakdowns)
        material_total = sum(b.material_cost for b in breakdowns)
        equipment_total = sum(b.equipment_cost for b in breakdowns)
        overhead_total = sum(b.overhead_cost for b in breakdowns)
        profit_total = sum(b.profit_cost for b in breakdowns)
        total_cost = sum(b.total_cost for b in breakdowns)

        # Group by category if requested
        breakdown_by_category = {}
        if group_by_category:
            for b in breakdowns:
                # Extract category from work item code prefix
                category = b.work_item_code.split('-')[0] if '-' in b.work_item_code else 'Other'
                if category not in breakdown_by_category:
                    breakdown_by_category[category] = 0
                breakdown_by_category[category] += b.total_cost

        return CostSummary(
            total_cost=total_cost,
            labor_total=labor_total,
            material_total=material_total,
            equipment_total=equipment_total,
            overhead_total=overhead_total,
            profit_total=profit_total,
            item_count=len(breakdowns),
            currency=self.currency,
            calculated_at=datetime.now(),
            breakdown_by_category=breakdown_by_category
        )

    def calculate_from_qto(self, qto_df: pd.DataFrame,
                          code_column: str = 'work_item_code',
                          quantity_column: str = 'quantity') -> pd.DataFrame:
        """Calculate costs from Quantity Takeoff DataFrame."""

        results = []
        for _, row in qto_df.iterrows():
            code = row[code_column]
            qty = row[quantity_column]

            breakdown = self.calculate_item_cost(code, qty)
            result = breakdown.to_dict()

            # Add original QTO columns
            for col in qto_df.columns:
                if col not in result:
                    result[f'qto_{col}'] = row[col]

            results.append(result)

        return pd.DataFrame(results)

    def apply_regional_factors(self, base_costs: pd.DataFrame,
                               region_factors: Dict[str, float]) -> pd.DataFrame:
        """Apply regional adjustment factors."""
        adjusted = base_costs.copy()

        if 'labor_cost' in adjusted.columns and 'labor' in region_factors:
            adjusted['labor_cost'] *= region_factors['labor']

        if 'material_cost' in adjusted.columns and 'material' in region_factors:
            adjusted['material_cost'] *= region_factors['material']

        if 'equipment_cost' in adjusted.columns and 'equipment' in region_factors:
            adjusted['equipment_cost'] *= region_factors['equipment']

        # Recalculate totals
        adjusted['direct_cost'] = (
            adjusted.get('labor_cost', 0) +
            adjusted.get('material_cost', 0) +
            adjusted.get('equipment_cost', 0)
        )
        adjusted['total_cost'] = adjusted['direct_cost'] * (1 + self.overhead_rate) * (1 + self.profit_rate)

        return adjusted

    def compare_estimates(self, estimate1: CostSummary,
                         estimate2: CostSummary) -> Dict[str, Any]:
        """Compare two cost estimates."""
        return {
            'total_difference': estimate2.total_cost - estimate1.total_cost,
            'total_percent_change': (
                (estimate2.total_cost - estimate1.total_cost) /
                estimate1.total_cost * 100 if estimate1.total_cost > 0 else 0
            ),
            'labor_difference': estimate2.labor_total - estimate1.labor_total,
            'material_difference': estimate2.material_total - estimate1.material_total,
            'equipment_difference': estimate2.equipment_total - estimate1.equipment_total,
            'item_count_difference': estimate2.item_count - estimate1.item_count
        }


class CostReportGenerator:
    """Generate cost reports from calculations."""

    def __init__(self, calculator: CWICRCostCalculator):
        self.calculator = calculator

    def generate_summary_report(self, items: List[Dict[str, Any]]) -> Dict[str, Any]:
        """Generate summary cost report."""
        summary = self.calculator.calculate_estimate(items)

        return {
            'report_date': datetime.now().isoformat(),
            'currency': summary.currency,
            'total_cost': round(summary.total_cost, 2),
            'breakdown': {
                'labor': round(summary.labor_total, 2),
                'material': round(summary.material_total, 2),
                'equipment': round(summary.equipment_total, 2),
                'overhead': round(summary.overhead_total, 2),
                'profit': round(summary.profit_total, 2)
            },
            'percentages': {
                'labor': round(summary.labor_total / summary.total_cost * 100, 1) if summary.total_cost > 0 else 0,
                'material': round(summary.material_total / summary.total_cost * 100, 1) if summary.total_cost > 0 else 0,
                'equipment': round(summary.equipment_total / summary.total_cost * 100, 1) if summary.total_cost > 0 else 0,
            },
            'item_count': summary.item_count,
            'by_category': summary.breakdown_by_category
        }

    def generate_detailed_report(self, items: List[Dict[str, Any]]) -> pd.DataFrame:
        """Generate detailed line-item report."""
        results = []

        for item in items:
            code = item.get('work_item_code') or item.get('code')
            qty = item.get('quantity', 0)

            breakdown = self.calculator.calculate_item_cost(code, qty)
            results.append(breakdown.to_dict())

        df = pd.DataFrame(results)

        # Add totals row
        totals = df[['labor_cost', 'material_cost', 'equipment_cost',
                     'overhead_cost', 'profit_cost', 'total_cost']].sum()
        totals['description'] = 'TOTAL'
        totals['work_item_code'] = ''

        df = pd.concat([df, pd.DataFrame([totals])], ignore_index=True)

        return df


# Convenience functions
def calculate_cost(cwicr_data: pd.DataFrame,
                   work_item_code: str,
                   quantity: float) -> float:
    """Quick cost calculation."""
    calc = CWICRCostCalculator(cwicr_data)
    breakdown = calc.calculate_item_cost(work_item_code, quantity)
    return breakdown.total_cost


def estimate_project_cost(cwicr_data: pd.DataFrame,
                         items: List[Dict[str, Any]]) -> Dict[str, Any]:
    """Quick project cost estimate."""
    calc = CWICRCostCalculator(cwicr_data)
    report = CostReportGenerator(calc)
    return report.generate_summary_report(items)

Quick Start

python
import pandas as pd
from cwicr_data_loader import CWICRDataLoader

# Load CWICR data
loader = CWICRDataLoader()
cwicr = loader.load("TR_workitems_costs_resources_DDC_CWICR.parquet")

# Initialize calculator
calc = CWICRCostCalculator(cwicr)

# Calculate single item
breakdown = calc.calculate_item_cost("CONC-001", quantity=150)
print(f"Total: ${breakdown.total_cost:,.2f}")
print(f"  Labor: ${breakdown.labor_cost:,.2f}")
print(f"  Material: ${breakdown.material_cost:,.2f}")
print(f"  Equipment: ${breakdown.equipment_cost:,.2f}")

Common Use Cases

1. Project Estimate

python
items = [
    {'work_item_code': 'CONC-001', 'quantity': 150},
    {'work_item_code': 'EXCV-002', 'quantity': 200},
    {'work_item_code': 'REBAR-003', 'quantity': 15000}  # kg
]

summary = calc.calculate_estimate(items)
print(f"Project Total: ${summary.total_cost:,.2f}")

2. QTO Integration

python
# Load BIM quantities
qto = pd.read_excel("quantities.xlsx")

# Calculate costs
costs = calc.calculate_from_qto(qto,
    code_column='work_item',
    quantity_column='quantity'
)
print(costs[['description', 'quantity', 'total_cost']])

3. Regional Adjustment

python
# Apply Berlin pricing
berlin_factors = {
    'labor': 1.15,      # 15% higher labor
    'material': 0.95,   # 5% lower materials
    'equipment': 1.0
}

adjusted = calc.apply_regional_factors(costs, berlin_factors)

Resources

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cwicr Cost Calculator AI skill do?

Calculate construction costs using DDC CWICR resource-based methodology. Break down costs into labor, materials, equipment with transparent pricing.

Why use Cwicr Cost Calculator on TypingMind?

Because you install it once and use it with any model. Cwicr Cost Calculator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cwicr Cost Calculator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/main/1_DDC_Toolkit/CWICR-Database/cwicr-cost-calculator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cwicr Cost Calculator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cwicr Cost Calculator?

As many as you like. As long as a model supports skills, you can use Cwicr Cost Calculator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cwicr Cost Calculator AI skill free?

Yes. It is published on GitHub by datadrivenconstruction under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇