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-work-breakdowngit 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-work-breakdown)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-work-breakdown"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-work-breakdown/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-work-breakdown"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-work-breakdown.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 | $0.03747 |
| Opus 5 | $0.00017 | $0.01873 |
| Sonnet 5 | $0.00007 | $0.00749 |
| Haiku 4.5 | $0.00003 | $0.00375 |
Grade A, and why
cwicr-work-breakdown 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-work-breakdown — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 469 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CWICR Work Breakdown
Business Case
Problem Statement
Work items in CWICR contain aggregated resources:
- What materials make up a concrete work item?
- What labor categories are needed?
- What equipment is involved?
- How to generate detailed resource bills?
Solution
Decompose CWICR work items into their constituent resources (labor, materials, equipment) with quantities and costs.
Business Value
- Transparency - See inside aggregated items
- Procurement - Generate material lists
- Scheduling - Identify resource needs
- Cost control - Track resource consumption
Technical Implementation
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from datetime import datetime
from enum import Enum
from collections import defaultdict
class ResourceType(Enum):
"""Types of resources in work items."""
LABOR = "labor"
MATERIAL = "material"
EQUIPMENT = "equipment"
OVERHEAD = "overhead"
@dataclass
class ResourceComponent:
"""Single resource component of a work item."""
resource_code: str
resource_type: ResourceType
description: str
unit: str
quantity_per_unit: float # Per unit of work item
unit_rate: float
cost_per_unit: float # Per unit of work item
@dataclass
class WorkItemBreakdown:
"""Complete breakdown of a work item."""
work_item_code: str
work_item_description: str
work_item_unit: str
components: List[ResourceComponent]
labor_cost_per_unit: float
material_cost_per_unit: float
equipment_cost_per_unit: float
total_cost_per_unit: float
@dataclass
class BillOfResources:
"""Bill of resources for multiple work items."""
project_name: str
total_labor_cost: float
total_material_cost: float
total_equipment_cost: float
total_cost: float
labor_resources: List[Dict[str, Any]]
material_resources: List[Dict[str, Any]]
equipment_resources: List[Dict[str, Any]]
class CWICRWorkBreakdown:
"""Break down work items into resources."""
def __init__(self, cwicr_data: pd.DataFrame,
resources_data: pd.DataFrame = None):
self.work_items = cwicr_data
self.resources = resources_data
self._index_data()
def _index_data(self):
"""Index data for fast lookup."""
if 'work_item_code' in self.work_items.columns:
self._work_index = self.work_items.set_index('work_item_code')
else:
self._work_index = None
if self.resources is not None and 'resource_code' in self.resources.columns:
self._resource_index = self.resources.set_index('resource_code')
else:
self._resource_index = None
def breakdown_work_item(self, work_item_code: str) -> Optional[WorkItemBreakdown]:
"""Break down single work item into components."""
if self._work_index is None or work_item_code not in self._work_index.index:
return None
item = self._work_index.loc[work_item_code]
components = []
# Extract labor component
labor_norm = float(item.get('labor_norm', 0) or 0)
labor_rate = float(item.get('labor_rate', 35) or 35)
labor_cost = float(item.get('labor_cost', labor_norm * labor_rate) or labor_norm * labor_rate)
if labor_norm > 0:
components.append(ResourceComponent(
resource_code=f"{work_item_code}-LABOR",
resource_type=ResourceType.LABOR,
description=f"Labor for {item.get('description', '')}",
unit="hr",
quantity_per_unit=labor_norm,
unit_rate=labor_rate,
cost_per_unit=labor_cost
))
# Extract material component
material_norm = float(item.get('material_norm', 1) or 1)
material_cost = float(item.get('material_cost', 0) or 0)
if material_cost > 0:
components.append(ResourceComponent(
resource_code=f"{work_item_code}-MAT",
resource_type=ResourceType.MATERIAL,
description=str(item.get('material_description', 'Materials')),
unit=str(item.get('material_unit', item.get('unit', 'ea'))),
quantity_per_unit=material_norm,
unit_rate=material_cost / material_norm if material_norm > 0 else material_cost,
cost_per_unit=material_cost
))
# Extract equipment component
equipment_norm = float(item.get('equipment_norm', 0) or 0)
equipment_rate = float(item.get('equipment_rate', 0) or 0)
equipment_cost = float(item.get('equipment_cost', equipment_norm * equipment_rate) or 0)
if equipment_norm > 0 or equipment_cost > 0:
components.append(ResourceComponent(
resource_code=f"{work_item_code}-EQUIP",
resource_type=ResourceType.EQUIPMENT,
description=str(item.get('equipment_description', 'Equipment')),
unit="hr",
quantity_per_unit=equipment_norm,
unit_rate=equipment_rate,
cost_per_unit=equipment_cost
))
return WorkItemBreakdown(
work_item_code=work_item_code,
work_item_description=str(item.get('description', '')),
work_item_unit=str(item.get('unit', '')),
components=components,
labor_cost_per_unit=labor_cost,
material_cost_per_unit=material_cost,
equipment_cost_per_unit=equipment_cost,
total_cost_per_unit=labor_cost + material_cost + equipment_cost
)
def generate_bill_of_resources(self,
items: List[Dict[str, Any]],
project_name: str = "Project") -> BillOfResources:
"""Generate bill of resources from work items."""
labor_agg = defaultdict(lambda: {'hours': 0, 'cost': 0, 'work_items': []})
material_agg = defaultdict(lambda: {'quantity': 0, 'cost': 0, 'unit': '', 'work_items': []})
equipment_agg = defaultdict(lambda: {'hours': 0, 'cost': 0, 'work_items': []})
for item in items:
code = item.get('work_item_code', item.get('code'))
qty = item.get('quantity', 0)
breakdown = self.breakdown_work_item(code)
if not breakdown:
continue
for component in breakdown.components:
scaled_qty = component.quantity_per_unit * qty
scaled_cost = component.cost_per_unit * qty
if component.resource_type == ResourceType.LABOR:
key = 'General Labor' # Could be more specific with skill data
labor_agg[key]['hours'] += scaled_qty
labor_agg[key]['cost'] += scaled_cost
labor_agg[key]['work_items'].append(code)
elif component.resource_type == ResourceType.MATERIAL:
key = component.description
material_agg[key]['quantity'] += scaled_qty
material_agg[key]['cost'] += scaled_cost
material_agg[key]['unit'] = component.unit
material_agg[key]['work_items'].append(code)
elif component.resource_type == ResourceType.EQUIPMENT:
key = component.description
equipment_agg[key]['hours'] += scaled_qty
equipment_agg[key]['cost'] += scaled_cost
equipment_agg[key]['work_items'].append(code)
# Convert to lists
labor_resources = [
{
'resource': name,
'hours': round(data['hours'], 1),
'cost': round(data['cost'], 2),
'work_items': len(set(data['work_items']))
}
for name, data in labor_agg.items()
]
material_resources = [
{
'resource': name,
'quantity': round(data['quantity'], 2),
'unit': data['unit'],
'cost': round(data['cost'], 2),
'work_items': len(set(data['work_items']))
}
for name, data in material_agg.items()
]
equipment_resources = [
{
'resource': name,
'hours': round(data['hours'], 1),
'cost': round(data['cost'], 2),
'work_items': len(set(data['work_items']))
}
for name, data in equipment_agg.items()
]
total_labor = sum(r['cost'] for r in labor_resources)
total_material = sum(r['cost'] for r in material_resources)
total_equipment = sum(r['cost'] for r in equipment_resources)
return BillOfResources(
project_name=project_name,
total_labor_cost=round(total_labor, 2),
total_material_cost=round(total_material, 2),
total_equipment_cost=round(total_equipment, 2),
total_cost=round(total_labor + total_material + total_equipment, 2),
labor_resources=labor_resources,
material_resources=material_resources,
equipment_resources=equipment_resources
)
def get_resource_composition(self, work_item_code: str) -> Dict[str, float]:
"""Get percentage composition of work item by resource type."""
breakdown = self.breakdown_work_item(work_item_code)
if not breakdown or breakdown.total_cost_per_unit == 0:
return {'labor': 0, 'material': 0, 'equipment': 0}
total = breakdown.total_cost_per_unit
return {
'labor': round(breakdown.labor_cost_per_unit / total * 100, 1),
'material': round(breakdown.material_cost_per_unit / total * 100, 1),
'equipment': round(breakdown.equipment_cost_per_unit / total * 100, 1)
}
def analyze_labor_intensity(self,
work_items: List[str]) -> pd.DataFrame:
"""Analyze labor intensity of work items."""
data = []
for code in work_items:
breakdown = self.breakdown_work_item(code)
if breakdown:
composition = self.get_resource_composition(code)
labor_components = [c for c in breakdown.components if c.resource_type == ResourceType.LABOR]
labor_hours = sum(c.quantity_per_unit for c in labor_components)
data.append({
'work_item_code': code,
'description': breakdown.work_item_description,
'labor_hours_per_unit': labor_hours,
'labor_cost_pct': composition['labor'],
'material_cost_pct': composition['material'],
'equipment_cost_pct': composition['equipment'],
'labor_intensive': composition['labor'] > 50
})
return pd.DataFrame(data).sort_values('labor_cost_pct', ascending=False)
def export_breakdown(self,
breakdown: WorkItemBreakdown,
output_path: str) -> str:
"""Export single work item breakdown."""
df = pd.DataFrame([
{
'Resource Code': c.resource_code,
'Type': c.resource_type.value,
'Description': c.description,
'Unit': c.unit,
'Quantity/Unit': c.quantity_per_unit,
'Rate': c.unit_rate,
'Cost/Unit': c.cost_per_unit
}
for c in breakdown.components
])
df.to_excel(output_path, index=False)
return output_path
def export_bill_of_resources(self,
bill: BillOfResources,
output_path: str) -> str:
"""Export bill of resources to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Summary
summary_df = pd.DataFrame([{
'Project': bill.project_name,
'Total Labor Cost': bill.total_labor_cost,
'Total Material Cost': bill.total_material_cost,
'Total Equipment Cost': bill.total_equipment_cost,
'Grand Total': bill.total_cost
}])
summary_df.to_excel(writer, sheet_name='Summary', index=False)
# Labor
labor_df = pd.DataFrame(bill.labor_resources)
labor_df.to_excel(writer, sheet_name='Labor', index=False)
# Materials
material_df = pd.DataFrame(bill.material_resources)
material_df.to_excel(writer, sheet_name='Materials', index=False)
# Equipment
equipment_df = pd.DataFrame(bill.equipment_resources)
equipment_df.to_excel(writer, sheet_name='Equipment', index=False)
return output_path
class ResourceAggregator:
"""Aggregate resources across work items."""
def __init__(self, breakdown_tool: CWICRWorkBreakdown):
self.breakdown = breakdown_tool
def aggregate_by_trade(self,
items: List[Dict[str, Any]]) -> Dict[str, Dict[str, float]]:
"""Aggregate resources by trade/category."""
by_trade = defaultdict(lambda: {'labor_hours': 0, 'labor_cost': 0, 'items': 0})
for item in items:
code = item.get('work_item_code', item.get('code'))
qty = item.get('quantity', 0)
# Extract trade from code prefix
trade = code.split('-')[0] if '-' in code else 'General'
breakdown = self.breakdown.breakdown_work_item(code)
if breakdown:
by_trade[trade]['labor_hours'] += breakdown.labor_cost_per_unit / 35 * qty # Estimate hours
by_trade[trade]['labor_cost'] += breakdown.labor_cost_per_unit * qty
by_trade[trade]['items'] += 1
return dict(by_trade)
def identify_critical_resources(self,
bill: BillOfResources,
threshold_pct: float = 10) -> Dict[str, List[Dict]]:
"""Identify resources that contribute significantly to cost."""
critical = {
'labor': [],
'material': [],
'equipment': []
}
# Labor
for r in bill.labor_resources:
if bill.total_labor_cost > 0:
pct = r['cost'] / bill.total_labor_cost * 100
if pct >= threshold_pct:
critical['labor'].append({**r, 'percentage': round(pct, 1)})
# Materials
for r in bill.material_resources:
if bill.total_material_cost > 0:
pct = r['cost'] / bill.total_material_cost * 100
if pct >= threshold_pct:
critical['material'].append({**r, 'percentage': round(pct, 1)})
# Equipment
for r in bill.equipment_resources:
if bill.total_equipment_cost > 0:
pct = r['cost'] / bill.total_equipment_cost * 100
if pct >= threshold_pct:
critical['equipment'].append({**r, 'percentage': round(pct, 1)})
return critical
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 · 469 lines · 34 tokens per session scan A cbd91d7be357
cwicr-work-breakdown 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 34 tokens to every session and 3,747 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
skill-builder
Automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
ecto-patterns
Ecto patterns — schemas, changesets, queries, migrations, Multi, associations, preloads, upserts. Use when editing Repo calls, Ecto.Query, or schema fields. Skip for Ash.
phx-research
Research Elixir/Phoenix/Ecto topics or evaluate Hex libraries (--library). Use when learning about libraries, patterns, or comparing approaches. Searches HexDocs, ElixirForum, GitHub.
document
Generate @moduledoc/@doc for tested Elixir features; may update their README section or ADR. Not for docs lookup, documentation audits/reviews, or capturing standalone decisions.