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-takeoff-helpergit 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-takeoff-helper)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-takeoff-helper"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-takeoff-helper/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-takeoff-helper"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-takeoff-helper.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 | $0.00034 | $0.03312 |
| Opus 5.5 | $0.00014 | $0.01325 |
| Sonnet 5.5 | $0.00007 | $0.00662 |
| Haiku 4.5 | $0.00003 | $0.00331 |
Grade A, and why
cwicr-takeoff-helper 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cwicr-takeoff-helper — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 444 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CWICR Takeoff Helper
Business Case
Problem Statement
Quantity takeoff requires:
- Accurate calculations from dimensions
- Correct unit conversions
- Waste factor application
- Complete scope coverage
Solution
Assist takeoff process with CWICR-based calculations, automatic waste factors, unit conversions, and related item suggestions.
Business Value
- Accuracy - Validated calculations
- Completeness - Related items suggested
- Speed - Quick quantity calculations
- Consistency - Standard approaches
Technical Implementation
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass
from enum import Enum
import math
class TakeoffType(Enum):
"""Types of takeoff calculations."""
LINEAR = "linear" # Length
AREA = "area" # Square measure
VOLUME = "volume" # Cubic measure
COUNT = "count" # Each/number
WEIGHT = "weight" # By weight
class UnitSystem(Enum):
"""Unit systems."""
METRIC = "metric"
IMPERIAL = "imperial"
@dataclass
class TakeoffItem:
"""Single takeoff item."""
work_item_code: str
description: str
takeoff_type: TakeoffType
gross_quantity: float
waste_factor: float
net_quantity: float
unit: str
dimensions: Dict[str, float]
calculation: str
@dataclass
class TakeoffResult:
"""Complete takeoff result."""
items: List[TakeoffItem]
total_items: int
related_suggestions: List[str]
# Unit conversion factors
CONVERSIONS = {
# Length
('m', 'ft'): 3.28084,
('ft', 'm'): 0.3048,
('m', 'in'): 39.3701,
('in', 'm'): 0.0254,
# Area
('m2', 'sf'): 10.7639,
('sf', 'm2'): 0.0929,
# Volume
('m3', 'cf'): 35.3147,
('cf', 'm3'): 0.0283,
('m3', 'cy'): 1.30795,
('cy', 'm3'): 0.7646,
# Weight
('kg', 'lb'): 2.20462,
('lb', 'kg'): 0.453592,
('ton', 'kg'): 1000,
('kg', 'ton'): 0.001
}
# Standard waste factors
WASTE_FACTORS = {
'concrete': 0.05,
'rebar': 0.08,
'formwork': 0.10,
'brick': 0.10,
'block': 0.08,
'drywall': 0.12,
'tile': 0.15,
'lumber': 0.12,
'roofing': 0.10,
'paint': 0.10,
'pipe': 0.05,
'wire': 0.05,
'duct': 0.08,
'default': 0.05
}
# Related work items by category
RELATED_ITEMS = {
'concrete': ['formwork', 'rebar', 'curing', 'finishing'],
'masonry': ['mortar', 'reinforcement', 'ties', 'lintels'],
'drywall': ['framing', 'insulation', 'taping', 'painting'],
'roofing': ['underlayment', 'flashing', 'ventilation', 'insulation'],
'flooring': ['underlayment', 'adhesive', 'trim', 'transitions']
}
class CWICRTakeoffHelper:
"""Assist with quantity takeoff using CWICR data."""
def __init__(self, cwicr_data: pd.DataFrame = None):
self.cwicr = cwicr_data
if cwicr_data is not None:
self._index_cwicr()
def _index_cwicr(self):
"""Index CWICR data."""
if 'work_item_code' in self.cwicr.columns:
self._cwicr_index = self.cwicr.set_index('work_item_code')
else:
self._cwicr_index = None
def convert_unit(self, value: float, from_unit: str, to_unit: str) -> float:
"""Convert between units."""
if from_unit == to_unit:
return value
key = (from_unit.lower(), to_unit.lower())
if key in CONVERSIONS:
return value * CONVERSIONS[key]
# Try reverse
reverse_key = (to_unit.lower(), from_unit.lower())
if reverse_key in CONVERSIONS:
return value / CONVERSIONS[reverse_key]
return value
def get_waste_factor(self, work_item_code: str) -> float:
"""Get waste factor for work item."""
code_lower = work_item_code.lower()
for material, factor in WASTE_FACTORS.items():
if material in code_lower:
return factor
return WASTE_FACTORS['default']
def calculate_area(self,
length: float,
width: float,
deductions: List[Tuple[float, float]] = None) -> Dict[str, float]:
"""Calculate area with deductions."""
gross_area = length * width
deduction_area = 0
if deductions:
for d_length, d_width in deductions:
deduction_area += d_length * d_width
net_area = gross_area - deduction_area
return {
'gross_area': round(gross_area, 2),
'deductions': round(deduction_area, 2),
'net_area': round(net_area, 2),
'calculation': f"{length} x {width} = {gross_area}, minus {deduction_area} deductions"
}
def calculate_volume(self,
length: float,
width: float,
depth: float) -> Dict[str, float]:
"""Calculate volume."""
volume = length * width * depth
return {
'volume': round(volume, 3),
'calculation': f"{length} x {width} x {depth} = {volume}"
}
def calculate_perimeter(self,
length: float,
width: float) -> Dict[str, float]:
"""Calculate perimeter."""
perimeter = 2 * (length + width)
return {
'perimeter': round(perimeter, 2),
'calculation': f"2 x ({length} + {width}) = {perimeter}"
}
def calculate_concrete(self,
length: float,
width: float,
thickness: float,
work_item_code: str = "CONC-001") -> TakeoffItem:
"""Calculate concrete quantity with related items."""
volume = length * width * thickness
waste = self.get_waste_factor(work_item_code)
net_qty = volume * (1 + waste)
return TakeoffItem(
work_item_code=work_item_code,
description="Concrete",
takeoff_type=TakeoffType.VOLUME,
gross_quantity=round(volume, 3),
waste_factor=waste,
net_quantity=round(net_qty, 3),
unit="m3",
dimensions={'length': length, 'width': width, 'thickness': thickness},
calculation=f"{length}m x {width}m x {thickness}m = {volume:.3f} m3 + {waste:.0%} waste"
)
def calculate_wall_area(self,
perimeter: float,
height: float,
openings: List[Tuple[float, float]] = None,
work_item_code: str = "WALL-001") -> TakeoffItem:
"""Calculate wall area with openings deducted."""
gross_area = perimeter * height
opening_area = 0
if openings:
for w, h in openings:
opening_area += w * h
net_area = gross_area - opening_area
waste = self.get_waste_factor(work_item_code)
order_qty = net_area * (1 + waste)
return TakeoffItem(
work_item_code=work_item_code,
description="Wall finish",
takeoff_type=TakeoffType.AREA,
gross_quantity=round(gross_area, 2),
waste_factor=waste,
net_quantity=round(order_qty, 2),
unit="m2",
dimensions={'perimeter': perimeter, 'height': height, 'openings': len(openings or [])},
calculation=f"{perimeter}m x {height}m = {gross_area:.2f} m2 - {opening_area:.2f} openings + {waste:.0%} waste"
)
def calculate_flooring(self,
length: float,
width: float,
work_item_code: str = "FLOOR-001") -> TakeoffItem:
"""Calculate flooring quantity."""
area = length * width
waste = self.get_waste_factor(work_item_code)
order_qty = area * (1 + waste)
return TakeoffItem(
work_item_code=work_item_code,
description="Flooring",
takeoff_type=TakeoffType.AREA,
gross_quantity=round(area, 2),
waste_factor=waste,
net_quantity=round(order_qty, 2),
unit="m2",
dimensions={'length': length, 'width': width},
calculation=f"{length}m x {width}m = {area:.2f} m2 + {waste:.0%} waste"
)
def calculate_rebar(self,
concrete_volume: float,
kg_per_m3: float = 100,
work_item_code: str = "REBAR-001") -> TakeoffItem:
"""Calculate rebar from concrete volume."""
weight = concrete_volume * kg_per_m3
waste = self.get_waste_factor(work_item_code)
order_qty = weight * (1 + waste)
return TakeoffItem(
work_item_code=work_item_code,
description="Reinforcement",
takeoff_type=TakeoffType.WEIGHT,
gross_quantity=round(weight, 1),
waste_factor=waste,
net_quantity=round(order_qty, 1),
unit="kg",
dimensions={'concrete_m3': concrete_volume, 'kg_per_m3': kg_per_m3},
calculation=f"{concrete_volume} m3 x {kg_per_m3} kg/m3 = {weight:.1f} kg + {waste:.0%} waste"
)
def suggest_related_items(self, work_item_code: str) -> List[str]:
"""Suggest related work items."""
code_lower = work_item_code.lower()
for category, related in RELATED_ITEMS.items():
if category in code_lower:
return related
return []
def room_takeoff(self,
length: float,
width: float,
height: float,
openings: List[Tuple[float, float]] = None) -> TakeoffResult:
"""Complete room takeoff."""
items = []
# Floor
floor = self.calculate_flooring(length, width, "FLOOR-001")
items.append(floor)
# Ceiling (same as floor)
ceiling = TakeoffItem(
work_item_code="CEIL-001",
description="Ceiling",
takeoff_type=TakeoffType.AREA,
gross_quantity=floor.gross_quantity,
waste_factor=floor.waste_factor,
net_quantity=floor.net_quantity,
unit="m2",
dimensions=floor.dimensions,
calculation=f"Same as floor: {floor.gross_quantity} m2"
)
items.append(ceiling)
# Walls
perimeter = 2 * (length + width)
walls = self.calculate_wall_area(perimeter, height, openings, "WALL-001")
items.append(walls)
# Related suggestions
suggestions = ['paint', 'baseboard', 'trim', 'electrical outlets']
return TakeoffResult(
items=items,
total_items=len(items),
related_suggestions=suggestions
)
def export_takeoff(self,
items: List[TakeoffItem],
output_path: str) -> str:
"""Export takeoff to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
df = pd.DataFrame([
{
'Work Item Code': item.work_item_code,
'Description': item.description,
'Type': item.takeoff_type.value,
'Gross Qty': item.gross_quantity,
'Waste %': f"{item.waste_factor:.0%}",
'Net Qty': item.net_quantity,
'Unit': item.unit,
'Calculation': item.calculation
}
for item in items
])
df.to_excel(writer, sheet_name='Takeoff', 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.
- 1mo ago First seen · 444 lines · 34 tokens per session scan A ced0665b9c19
cwicr-takeoff-helper is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (374 stars, last pushed 8d ago), licensed MIT. It adds 34 tokens to every session and 3,312 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
agent-era-pricing
Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or outcome-based pricing, to price an agent/API tier, or to defend revenue as customers automate their own usage. Produces a pricing…
invest-backup
Back up / restore openInvest's local state — memory/ (holdings, strategy, user profile, committee records, dream logs) + db/ (trade ledger, job run history, market-data cache) + .env (SMTP/API credentials) + userprofile.json. All of this data is .gitignore'd with no historical versions in git, so a single accidental…
job-profitability-analyzer
Find out which clients and jobs actually make money -- allocate real costs (labor hours, materials, subs, overhead) against what each job billed, and rank every client by true margin. Most service businesses discover their biggest client is their least profitable.
peer-bench
Peer benchmarking, multi-ticker financial comparison, growth value matrix, composite z-score ranking, industry peer comparison, competitive benchmarking, sector relative performance, peer group analysis, industry leader comparison, financial ratio benchmarking.
fda-catalyst-vaccines
Vaccine catalyst analysis across the two-gate path: CBER BLA review and the ACIP recommendation gate that turns FDA approval into commercial availability. Lot release, procurement milestones, pediatric bridging, and healthy-population efficacy context — dated, verified, and sized per event.
trading-as-business
Trading as a business, performance review process, trade journaling, capital allocation discipline, business infrastructure for traders, KPI tracking for trading operations.