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 datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill cwicr-waste-calculatorgit clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_ConstructionWrote 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/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-waste-calculator)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-waste-calculator"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-waste-calculator/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/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-waste-calculator"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-waste-calculator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.03758 |
| Opus 5 | $0.00017 | $0.01879 |
| Sonnet 5 | $0.00007 | $0.00752 |
| Haiku 4.5 | $0.00003 | $0.00376 |
Grade A, and why
cwicr-waste-calculator 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cwicr-waste-calculator — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 395 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CWICR Waste Calculator
Business Case
Problem Statement
Material estimates need waste factors:
- Cutting/trimming losses
- Spillage and breakage
- Overordering requirements
- Different waste by material type
Solution
Systematic waste calculation using CWICR material data with industry-standard waste factors by material category.
Business Value
- Accurate ordering - Include realistic waste
- Cost control - Budget for actual usage
- Sustainability - Track and reduce waste
- Benchmarking - Compare waste across projects
Technical Implementation
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional
from dataclasses import dataclass
from enum import Enum
class WasteCategory(Enum):
"""Waste category types."""
CUTTING = "cutting" # Cutting/trimming losses
SPILLAGE = "spillage" # Liquid material spillage
BREAKAGE = "breakage" # Damaged materials
OVERRUN = "overrun" # Installation overrun
THEFT = "theft" # Site theft allowance
WEATHER = "weather" # Weather damage
@dataclass
class WasteFactor:
"""Waste factor for a material."""
material_code: str
material_name: str
base_quantity: float
unit: str
cutting_waste_pct: float
spillage_pct: float
breakage_pct: float
overrun_pct: float
total_waste_pct: float
quantity_with_waste: float
waste_quantity: float
waste_cost: float
# Industry standard waste factors by material type
WASTE_FACTORS = {
'concrete': {
'cutting': 0.02, 'spillage': 0.03, 'breakage': 0.0, 'overrun': 0.02
},
'rebar': {
'cutting': 0.05, 'spillage': 0.0, 'breakage': 0.01, 'overrun': 0.02
},
'brick': {
'cutting': 0.05, 'spillage': 0.0, 'breakage': 0.03, 'overrun': 0.02
},
'block': {
'cutting': 0.04, 'spillage': 0.0, 'breakage': 0.02, 'overrun': 0.02
},
'lumber': {
'cutting': 0.10, 'spillage': 0.0, 'breakage': 0.02, 'overrun': 0.03
},
'plywood': {
'cutting': 0.12, 'spillage': 0.0, 'breakage': 0.02, 'overrun': 0.02
},
'drywall': {
'cutting': 0.10, 'spillage': 0.0, 'breakage': 0.03, 'overrun': 0.02
},
'tile': {
'cutting': 0.10, 'spillage': 0.0, 'breakage': 0.05, 'overrun': 0.03
},
'paint': {
'cutting': 0.0, 'spillage': 0.05, 'breakage': 0.0, 'overrun': 0.10
},
'mortar': {
'cutting': 0.0, 'spillage': 0.05, 'breakage': 0.0, 'overrun': 0.03
},
'insulation': {
'cutting': 0.08, 'spillage': 0.0, 'breakage': 0.02, 'overrun': 0.03
},
'roofing': {
'cutting': 0.10, 'spillage': 0.0, 'breakage': 0.02, 'overrun': 0.05
},
'pipe': {
'cutting': 0.05, 'spillage': 0.0, 'breakage': 0.01, 'overrun': 0.02
},
'wire': {
'cutting': 0.03, 'spillage': 0.0, 'breakage': 0.0, 'overrun': 0.05
},
'conduit': {
'cutting': 0.05, 'spillage': 0.0, 'breakage': 0.01, 'overrun': 0.02
},
'duct': {
'cutting': 0.08, 'spillage': 0.0, 'breakage': 0.01, 'overrun': 0.03
},
'steel': {
'cutting': 0.03, 'spillage': 0.0, 'breakage': 0.0, 'overrun': 0.02
},
'glass': {
'cutting': 0.05, 'spillage': 0.0, 'breakage': 0.05, 'overrun': 0.02
},
'flooring': {
'cutting': 0.10, 'spillage': 0.0, 'breakage': 0.02, 'overrun': 0.03
},
'adhesive': {
'cutting': 0.0, 'spillage': 0.08, 'breakage': 0.0, 'overrun': 0.05
},
'default': {
'cutting': 0.05, 'spillage': 0.02, 'breakage': 0.02, 'overrun': 0.03
}
}
class CWICRWasteCalculator:
"""Calculate material waste using CWICR data."""
def __init__(self, cwicr_data: pd.DataFrame):
self.materials = cwicr_data
self._index_data()
def _index_data(self):
"""Index materials data."""
if 'material_code' in self.materials.columns:
self._mat_index = self.materials.set_index('material_code')
elif 'work_item_code' in self.materials.columns:
self._mat_index = self.materials.set_index('work_item_code')
else:
self._mat_index = None
def _detect_material_type(self, description: str) -> str:
"""Detect material type from description."""
desc_lower = str(description).lower()
for mat_type in WASTE_FACTORS.keys():
if mat_type in desc_lower:
return mat_type
# Check common synonyms
synonyms = {
'concrete': ['beton', 'cement'],
'rebar': ['reinforcement', 'armature', 'арматура'],
'brick': ['кирпич', 'block'],
'lumber': ['wood', 'timber', 'древесина'],
'drywall': ['gypsum', 'plasterboard', 'гипсокартон'],
'tile': ['ceramic', 'плитка', 'керамика'],
'paint': ['краска', 'coating'],
'insulation': ['изоляция', 'утеплитель'],
'pipe': ['труба', 'piping'],
'wire': ['провод', 'cable', 'кабель']
}
for mat_type, words in synonyms.items():
if any(word in desc_lower for word in words):
return mat_type
return 'default'
def get_waste_factors(self, material_type: str) -> Dict[str, float]:
"""Get waste factors for material type."""
return WASTE_FACTORS.get(material_type, WASTE_FACTORS['default'])
def calculate_waste(self,
material_code: str,
base_quantity: float,
unit_cost: float = 0,
custom_factors: Dict[str, float] = None) -> WasteFactor:
"""Calculate waste for a material."""
# Get material info
material_name = material_code
unit = "unit"
if self._mat_index is not None and material_code in self._mat_index.index:
mat = self._mat_index.loc[material_code]
material_name = str(mat.get('description', mat.get('material_description', material_code)))
unit = str(mat.get('unit', mat.get('material_unit', 'unit')))
if unit_cost == 0:
unit_cost = float(mat.get('material_cost', mat.get('unit_cost', 0)) or 0)
# Detect material type and get factors
mat_type = self._detect_material_type(material_name)
factors = custom_factors or self.get_waste_factors(mat_type)
cutting = factors.get('cutting', 0)
spillage = factors.get('spillage', 0)
breakage = factors.get('breakage', 0)
overrun = factors.get('overrun', 0)
# Calculate total waste
total_waste_pct = cutting + spillage + breakage + overrun
waste_quantity = base_quantity * total_waste_pct
quantity_with_waste = base_quantity + waste_quantity
waste_cost = waste_quantity * unit_cost
return WasteFactor(
material_code=material_code,
material_name=material_name,
base_quantity=base_quantity,
unit=unit,
cutting_waste_pct=round(cutting * 100, 1),
spillage_pct=round(spillage * 100, 1),
breakage_pct=round(breakage * 100, 1),
overrun_pct=round(overrun * 100, 1),
total_waste_pct=round(total_waste_pct * 100, 1),
quantity_with_waste=round(quantity_with_waste, 2),
waste_quantity=round(waste_quantity, 2),
waste_cost=round(waste_cost, 2)
)
def calculate_project_waste(self,
materials: List[Dict[str, Any]]) -> Dict[str, Any]:
"""Calculate waste for entire project."""
results = []
total_base_cost = 0
total_waste_cost = 0
for mat in materials:
code = mat.get('material_code', mat.get('code'))
qty = mat.get('quantity', 0)
cost = mat.get('unit_cost', 0)
custom = mat.get('waste_factors')
waste = self.calculate_waste(code, qty, cost, custom)
results.append(waste)
total_base_cost += qty * cost
total_waste_cost += waste.waste_cost
# Summary by waste category
by_category = {
'cutting': sum(r.cutting_waste_pct * r.base_quantity / 100 for r in results),
'spillage': sum(r.spillage_pct * r.base_quantity / 100 for r in results),
'breakage': sum(r.breakage_pct * r.base_quantity / 100 for r in results),
'overrun': sum(r.overrun_pct * r.base_quantity / 100 for r in results)
}
return {
'materials': results,
'total_base_cost': round(total_base_cost, 2),
'total_waste_cost': round(total_waste_cost, 2),
'waste_percentage': round(total_waste_cost / total_base_cost * 100, 1) if total_base_cost > 0 else 0,
'by_category': by_category,
'order_quantity_increase': round(sum(r.waste_quantity for r in results), 2)
}
def optimize_cutting(self,
material_code: str,
required_lengths: List[float],
stock_length: float) -> Dict[str, Any]:
"""Optimize cutting to minimize waste (1D cutting stock problem)."""
# Simple first-fit decreasing algorithm
sorted_lengths = sorted(required_lengths, reverse=True)
stock_pieces = []
waste_per_piece = []
for length in sorted_lengths:
placed = False
for i, remaining in enumerate(stock_pieces):
if remaining >= length:
stock_pieces[i] -= length
placed = True
break
if not placed:
stock_pieces.append(stock_length - length)
total_stock_needed = len(stock_pieces)
total_material = total_stock_needed * stock_length
total_used = sum(required_lengths)
total_waste = total_material - total_used
waste_pct = total_waste / total_material * 100 if total_material > 0 else 0
return {
'material_code': material_code,
'stock_pieces_needed': total_stock_needed,
'stock_length': stock_length,
'total_material': round(total_material, 2),
'total_used': round(total_used, 2),
'total_waste': round(total_waste, 2),
'waste_percentage': round(waste_pct, 1),
'cutting_efficiency': round(100 - waste_pct, 1)
}
def export_waste_report(self,
project_waste: Dict[str, Any],
output_path: str) -> str:
"""Export waste report to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Summary
summary_df = pd.DataFrame([{
'Total Base Cost': project_waste['total_base_cost'],
'Total Waste Cost': project_waste['total_waste_cost'],
'Waste Percentage': project_waste['waste_percentage'],
'Order Increase': project_waste['order_quantity_increase']
}])
summary_df.to_excel(writer, sheet_name='Summary', index=False)
# Materials
mat_df = pd.DataFrame([
{
'Material': m.material_name,
'Base Qty': m.base_quantity,
'Unit': m.unit,
'Cutting %': m.cutting_waste_pct,
'Spillage %': m.spillage_pct,
'Breakage %': m.breakage_pct,
'Overrun %': m.overrun_pct,
'Total Waste %': m.total_waste_pct,
'Order Qty': m.quantity_with_waste,
'Waste Cost': m.waste_cost
}
for m in project_waste['materials']
])
mat_df.to_excel(writer, sheet_name='Materials', index=False)
return output_path
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.
- 13d ago First seen · 395 lines · 35 tokens per session scan A f4021bda6897
cwicr-waste-calculator is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (310 stars, last pushed 21d ago), licensed MIT. It adds 35 tokens to every session and 3,758 once invoked, about $0.0002 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
cmsis-dsp-integration
Use when integrating, configuring, or debugging CMSIS-DSP, ARM math functions, FFT, filters, fixed-point DSP, vector math, or Cortex-M signal processing.
Lab Report Writer
Generate professional lab reports for university courses, scientific research, engineering tests, and medical/material experiments. Supports three input modes (topic/raw data/draft improvement), auto-research with WebSearch, data tables & chart generation, error analysis, and output as docx/markdown. Use when writing…
carbon-accounting
Analyze carbon accounting and emissions tracking software for Scope 1/2/3 calculation accuracy, GHG Protocol compliance, offset verification, supply chain emissions, reporting standards (CDP, TCFD, GRI, SASB, SEC), reduction target tracking, and audit trail integrity..
disaster-prediction
Analyze disaster prediction and early warning systems — model accuracy for flood, earthquake, wildfire, hurricane, and tsunami hazards, data pipeline reliability from sensor networks and satellite feeds, alert distribution latency and channel coverage.
extraction-optimization
Optimize mining extraction operations by analyzing ore grade control, processing plant throughput, metallurgical recovery rates, energy consumption, and water balance.
load-forecast
Analyze energy load forecasting systems including demand prediction models (ARIMA, Prophet, LSTM), weather API integration, peak shaving strategies, demand response program optimization, renewable intermittency handling, net load duck curve management.