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 estimate-buildergit 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/estimate-builder)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/estimate-builder"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/estimate-builder/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/estimate-builder"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/estimate-builder.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 | $0.00023 | $0.02263 |
| Opus 5.5 | $0.00009 | $0.00905 |
| Sonnet 5.5 | $0.00005 | $0.00453 |
| Haiku 4.5 | $0.00002 | $0.00226 |
Grade A, and why
estimate-builder 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:
- estimate-builder — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 323 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Estimate Builder
Business Case
Problem Statement
Estimate creation challenges:
- Complex cost structures
- Multiple cost categories
- Markup calculations
- Format requirements vary
Solution
Structured estimate builder that creates professional construction estimates with proper cost categorization, markups, and export capabilities.
Technical Implementation
import pandas as pd
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from datetime import date
from enum import Enum
class CostCategory(Enum):
LABOR = "labor"
MATERIAL = "material"
EQUIPMENT = "equipment"
SUBCONTRACTOR = "subcontractor"
OTHER = "other"
@dataclass
class EstimateLineItem:
line_number: int
wbs_code: str
description: str
quantity: float
unit: str
unit_cost: float
category: CostCategory
notes: str = ""
@property
def total_cost(self) -> float:
return round(self.quantity * self.unit_cost, 2)
@dataclass
class CostSummary:
labor: float = 0
material: float = 0
equipment: float = 0
subcontractor: float = 0
other: float = 0
@property
def direct_cost(self) -> float:
return self.labor + self.material + self.equipment + self.subcontractor + self.other
@dataclass
class Markup:
name: str
rate: float # As decimal (0.10 = 10%)
base: str = "direct" # "direct" or "subtotal"
class EstimateBuilder:
"""Build construction project estimates."""
def __init__(self, project_name: str, project_number: str = ""):
self.project_name = project_name
self.project_number = project_number
self.estimate_date = date.today()
self.items: List[EstimateLineItem] = []
self.markups: List[Markup] = []
self._next_line = 1
def add_item(self,
wbs_code: str,
description: str,
quantity: float,
unit: str,
unit_cost: float,
category: CostCategory = CostCategory.OTHER,
notes: str = "") -> EstimateLineItem:
"""Add line item to estimate."""
item = EstimateLineItem(
line_number=self._next_line,
wbs_code=wbs_code,
description=description,
quantity=quantity,
unit=unit,
unit_cost=unit_cost,
category=category,
notes=notes
)
self.items.append(item)
self._next_line += 1
return item
def add_markup(self, name: str, rate: float, base: str = "direct"):
"""Add markup (overhead, profit, contingency, etc.)."""
self.markups.append(Markup(name=name, rate=rate, base=base))
def set_standard_markups(self,
overhead: float = 0.15,
profit: float = 0.10,
contingency: float = 0.05):
"""Set standard construction markups."""
self.markups = [
Markup("General Conditions / Overhead", overhead, "direct"),
Markup("Profit", profit, "subtotal"),
Markup("Contingency", contingency, "subtotal")
]
def get_cost_summary(self) -> CostSummary:
"""Get cost summary by category."""
summary = CostSummary()
for item in self.items:
cost = item.total_cost
if item.category == CostCategory.LABOR:
summary.labor += cost
elif item.category == CostCategory.MATERIAL:
summary.material += cost
elif item.category == CostCategory.EQUIPMENT:
summary.equipment += cost
elif item.category == CostCategory.SUBCONTRACTOR:
summary.subcontractor += cost
else:
summary.other += cost
return summary
def calculate_total(self) -> Dict[str, Any]:
"""Calculate total estimate with markups."""
summary = self.get_cost_summary()
direct_cost = summary.direct_cost
markups_detail = []
subtotal = direct_cost
for markup in self.markups:
if markup.base == "direct":
amount = direct_cost * markup.rate
else:
amount = subtotal * markup.rate
markups_detail.append({
'name': markup.name,
'rate': f"{markup.rate * 100:.1f}%",
'amount': round(amount, 2)
})
subtotal += amount
return {
'cost_summary': {
'labor': round(summary.labor, 2),
'material': round(summary.material, 2),
'equipment': round(summary.equipment, 2),
'subcontractor': round(summary.subcontractor, 2),
'other': round(summary.other, 2),
'direct_cost': round(direct_cost, 2)
},
'markups': markups_detail,
'total_markups': round(subtotal - direct_cost, 2),
'grand_total': round(subtotal, 2)
}
def get_items_by_wbs(self) -> Dict[str, List[EstimateLineItem]]:
"""Group items by WBS code prefix."""
by_wbs = {}
for item in self.items:
prefix = item.wbs_code.split('.')[0] if '.' in item.wbs_code else item.wbs_code
if prefix not in by_wbs:
by_wbs[prefix] = []
by_wbs[prefix].append(item)
return by_wbs
def import_from_df(self, df: pd.DataFrame):
"""Import line items from DataFrame."""
for _, row in df.iterrows():
self.add_item(
wbs_code=str(row.get('wbs_code', '')),
description=row['description'],
quantity=float(row['quantity']),
unit=row['unit'],
unit_cost=float(row['unit_cost']),
category=CostCategory(row.get('category', 'other').lower()),
notes=row.get('notes', '')
)
def export_to_df(self) -> pd.DataFrame:
"""Export estimate to DataFrame."""
data = []
for item in self.items:
data.append({
'Line': item.line_number,
'WBS': item.wbs_code,
'Description': item.description,
'Qty': item.quantity,
'Unit': item.unit,
'Unit Cost': item.unit_cost,
'Total': item.total_cost,
'Category': item.category.value,
'Notes': item.notes
})
return pd.DataFrame(data)
def export_to_excel(self, output_path: str) -> str:
"""Export estimate to Excel."""
totals = self.calculate_total()
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Cover sheet
cover_df = pd.DataFrame([{
'Project Name': self.project_name,
'Project Number': self.project_number,
'Estimate Date': self.estimate_date,
'Total Items': len(self.items),
'Direct Cost': totals['cost_summary']['direct_cost'],
'Grand Total': totals['grand_total']
}])
cover_df.to_excel(writer, sheet_name='Summary', index=False)
# Line items
items_df = self.export_to_df()
items_df.to_excel(writer, sheet_name='Line Items', index=False)
# Cost breakdown
breakdown_df = pd.DataFrame([totals['cost_summary']])
breakdown_df.to_excel(writer, sheet_name='Cost Breakdown', index=False)
# Markups
if totals['markups']:
markups_df = pd.DataFrame(totals['markups'])
markups_df.to_excel(writer, sheet_name='Markups', index=False)
return output_path
def validate(self) -> List[str]:
"""Validate estimate for common issues."""
issues = []
if not self.items:
issues.append("Estimate has no line items")
for item in self.items:
if item.quantity <= 0:
issues.append(f"Line {item.line_number}: Invalid quantity")
if item.unit_cost < 0:
issues.append(f"Line {item.line_number}: Negative unit cost")
if not item.description:
issues.append(f"Line {item.line_number}: Missing description")
if not self.markups:
issues.append("No markups defined (overhead, profit)")
return issues
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 · 323 lines · 23 tokens per session scan A e8dea0e800b6
estimate-builder 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 23 tokens to every session and 2,263 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 2026-09-03.
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.