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 jdmorag97-rgb/DDC_Skills_for_AI_Agents_in_Construction --skill cwicr-overhead-markupgit clone --depth 1 https://github.com/jdmorag97-rgb/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/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/cwicr-overhead-markup)<a href="https://agentmods.dev/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/cwicr-overhead-markup"><img src="https://agentmods.dev/badge/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/cwicr-overhead-markup/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/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/cwicr-overhead-markup"><img src="https://agentmods.dev/badge/skills/jdmorag97-rgb/ddc_skills_for_ai_agents_in_construction/cwicr-overhead-markup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00032 | $0.03007 |
| Opus 5 | $0.00016 | $0.01503 |
| Sonnet 5 | $0.00006 | $0.00601 |
| Haiku 4.5 | $0.00003 | $0.00301 |
Grade A, and why
cwicr-overhead-markup 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 12d 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.
This is a copy
100% identical to cwicr-overhead-markup — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 412 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CWICR Overhead & Markup Calculator
Business Case
Problem Statement
Direct costs need additional markups:
- General overhead (office, insurance)
- Project overhead (site costs)
- Profit margins
- Bonds and insurance
Solution
Systematic markup application to CWICR direct costs with configurable rates for overhead, profit, bonds, and other indirect costs.
Business Value
- Complete pricing - From cost to selling price
- Configurable rates - By project/client type
- Transparency - Clear markup breakdown
- Consistency - Standard markup application
Technical Implementation
import pandas as pd
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from enum import Enum
class MarkupType(Enum):
"""Types of markup."""
OVERHEAD = "overhead"
PROFIT = "profit"
BOND = "bond"
INSURANCE = "insurance"
CONTINGENCY = "contingency"
TAX = "tax"
ESCALATION = "escalation"
CUSTOM = "custom"
class MarkupMethod(Enum):
"""Markup calculation methods."""
ON_COST = "on_cost" # Markup on direct cost
ON_COST_PLUS = "on_cost_plus" # Markup on cost + previous markups
FIXED = "fixed" # Fixed amount
@dataclass
class MarkupItem:
"""Single markup item."""
name: str
markup_type: MarkupType
rate: float
method: MarkupMethod
base_amount: float
markup_amount: float
@dataclass
class MarkupSchedule:
"""Complete markup schedule."""
name: str
markups: List[MarkupItem]
def get_total_rate(self) -> float:
"""Get combined markup rate."""
return sum(m.rate for m in self.markups)
@dataclass
class PricingResult:
"""Complete pricing with all markups."""
direct_cost: float
labor_cost: float
material_cost: float
equipment_cost: float
subcontractor_cost: float
markups: List[MarkupItem]
total_markup: float
total_price: float
markup_percentage: float
# Standard markup templates
MARKUP_TEMPLATES = {
'residential': {
'overhead': 0.10,
'profit': 0.10,
'contingency': 0.05
},
'commercial': {
'overhead': 0.12,
'profit': 0.08,
'bond': 0.015,
'insurance': 0.02,
'contingency': 0.05
},
'industrial': {
'overhead': 0.15,
'profit': 0.08,
'bond': 0.02,
'insurance': 0.025,
'contingency': 0.08
},
'government': {
'overhead': 0.12,
'profit': 0.06,
'bond': 0.025,
'contingency': 0.05
},
'subcontractor': {
'overhead': 0.08,
'profit': 0.10
}
}
class CWICROverheadMarkup:
"""Apply overhead and markup to CWICR estimates."""
def __init__(self, cwicr_data: pd.DataFrame = None):
self.cost_data = cwicr_data
if cwicr_data is not None:
self._index_data()
def _index_data(self):
"""Index cost data."""
if 'work_item_code' in self.cost_data.columns:
self._code_index = self.cost_data.set_index('work_item_code')
else:
self._code_index = None
def get_template(self, template_name: str) -> Dict[str, float]:
"""Get markup template."""
return MARKUP_TEMPLATES.get(template_name, MARKUP_TEMPLATES['commercial'])
def create_markup_schedule(self,
name: str,
markups: Dict[str, float],
method: MarkupMethod = MarkupMethod.ON_COST) -> MarkupSchedule:
"""Create markup schedule from rates."""
items = []
for markup_name, rate in markups.items():
markup_type = MarkupType.CUSTOM
for mt in MarkupType:
if mt.value in markup_name.lower():
markup_type = mt
break
items.append(MarkupItem(
name=markup_name,
markup_type=markup_type,
rate=rate,
method=method,
base_amount=0,
markup_amount=0
))
return MarkupSchedule(name=name, markups=items)
def apply_markups(self,
direct_cost: float,
schedule: MarkupSchedule,
cost_breakdown: Dict[str, float] = None) -> PricingResult:
"""Apply markup schedule to direct cost."""
if cost_breakdown is None:
cost_breakdown = {
'labor': direct_cost * 0.40,
'material': direct_cost * 0.45,
'equipment': direct_cost * 0.10,
'subcontractor': direct_cost * 0.05
}
markup_items = []
running_total = direct_cost
for markup in schedule.markups:
if markup.method == MarkupMethod.ON_COST:
base = direct_cost
elif markup.method == MarkupMethod.ON_COST_PLUS:
base = running_total
else: # FIXED
base = 1
amount = base * markup.rate
markup_items.append(MarkupItem(
name=markup.name,
markup_type=markup.markup_type,
rate=markup.rate,
method=markup.method,
base_amount=round(base, 2),
markup_amount=round(amount, 2)
))
running_total += amount
total_markup = running_total - direct_cost
markup_pct = (total_markup / direct_cost * 100) if direct_cost > 0 else 0
return PricingResult(
direct_cost=round(direct_cost, 2),
labor_cost=round(cost_breakdown.get('labor', 0), 2),
material_cost=round(cost_breakdown.get('material', 0), 2),
equipment_cost=round(cost_breakdown.get('equipment', 0), 2),
subcontractor_cost=round(cost_breakdown.get('subcontractor', 0), 2),
markups=markup_items,
total_markup=round(total_markup, 2),
total_price=round(running_total, 2),
markup_percentage=round(markup_pct, 1)
)
def price_estimate(self,
items: List[Dict[str, Any]],
template: str = 'commercial') -> PricingResult:
"""Price complete estimate with markups."""
# Calculate direct costs
labor = 0
material = 0
equipment = 0
subcontractor = 0
for item in items:
code = item.get('work_item_code', item.get('code'))
qty = item.get('quantity', 0)
if self._code_index is not None and code in self._code_index.index:
wi = self._code_index.loc[code]
labor += float(wi.get('labor_cost', 0) or 0) * qty
material += float(wi.get('material_cost', 0) or 0) * qty
equipment += float(wi.get('equipment_cost', 0) or 0) * qty
subcontractor += item.get('subcontractor_cost', 0)
direct_cost = labor + material + equipment + subcontractor
cost_breakdown = {
'labor': labor,
'material': material,
'equipment': equipment,
'subcontractor': subcontractor
}
# Get template and create schedule
rates = self.get_template(template)
schedule = self.create_markup_schedule(template, rates)
return self.apply_markups(direct_cost, schedule, cost_breakdown)
def calculate_bid_price(self,
direct_cost: float,
overhead_rate: float = 0.12,
profit_rate: float = 0.08,
bond_rate: float = 0.015,
contingency_rate: float = 0.05) -> Dict[str, Any]:
"""Calculate bid price with standard markups."""
overhead = direct_cost * overhead_rate
subtotal1 = direct_cost + overhead
profit = subtotal1 * profit_rate
subtotal2 = subtotal1 + profit
bond = subtotal2 * bond_rate
subtotal3 = subtotal2 + bond
contingency = direct_cost * contingency_rate
total = subtotal3 + contingency
return {
'direct_cost': round(direct_cost, 2),
'overhead': round(overhead, 2),
'overhead_rate': f"{overhead_rate:.1%}",
'profit': round(profit, 2),
'profit_rate': f"{profit_rate:.1%}",
'bond': round(bond, 2),
'bond_rate': f"{bond_rate:.1%}",
'contingency': round(contingency, 2),
'contingency_rate': f"{contingency_rate:.1%}",
'bid_price': round(total, 2),
'total_markup': round(total - direct_cost, 2),
'total_markup_pct': round((total - direct_cost) / direct_cost * 100, 1)
}
def compare_markup_scenarios(self,
direct_cost: float,
scenarios: Dict[str, Dict[str, float]]) -> pd.DataFrame:
"""Compare different markup scenarios."""
results = []
for name, rates in scenarios.items():
schedule = self.create_markup_schedule(name, rates)
pricing = self.apply_markups(direct_cost, schedule)
results.append({
'Scenario': name,
'Direct Cost': pricing.direct_cost,
'Total Markup': pricing.total_markup,
'Markup %': pricing.markup_percentage,
'Total Price': pricing.total_price
})
return pd.DataFrame(results)
def export_pricing(self,
result: PricingResult,
output_path: str) -> str:
"""Export pricing breakdown to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Summary
summary_df = pd.DataFrame([{
'Direct Cost': result.direct_cost,
'Labor': result.labor_cost,
'Material': result.material_cost,
'Equipment': result.equipment_cost,
'Subcontractor': result.subcontractor_cost,
'Total Markup': result.total_markup,
'Markup %': result.markup_percentage,
'Total Price': result.total_price
}])
summary_df.to_excel(writer, sheet_name='Summary', index=False)
# Markup Details
markup_df = pd.DataFrame([
{
'Markup': m.name,
'Type': m.markup_type.value,
'Rate': f"{m.rate:.1%}",
'Base': m.base_amount,
'Amount': m.markup_amount
}
for m in result.markups
])
markup_df.to_excel(writer, sheet_name='Markups', 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.
- 12d ago First seen · 412 lines · 32 tokens per session scan A 3cf59acca2de
cwicr-overhead-markup is a skill published in the GitHub repository jdmorag97-rgb/DDC_Skills_for_AI_Agents_in_Construction (2 stars, last pushed 6mo ago), licensed MIT. It adds 32 tokens to every session and 3,007 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to cwicr-overhead-markup, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…