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-assembly-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/cwicr-assembly-builder)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-assembly-builder"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-assembly-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/cwicr-assembly-builder"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/cwicr-assembly-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 | $0.00028 | $0.03337 |
| Opus 5 | $0.00014 | $0.01669 |
| Sonnet 5 | $0.00006 | $0.00667 |
| Haiku 4.5 | $0.00003 | $0.00334 |
Grade A, and why
cwicr-assembly-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 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- cwicr-assembly-builder — 100% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 438 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CWICR Assembly Builder
Business Case
Problem Statement
Estimating repetitive elements requires:
- Consistent item groupings
- Reusable templates
- Standard assemblies
- Quick application
Solution
Build and manage assemblies of CWICR work items that can be applied as templates to speed up estimating and ensure completeness.
Business Value
- Speed - Apply complete assemblies quickly
- Consistency - Standard item groupings
- Completeness - No missed items
- Reusability - Template library
Technical Implementation
import pandas as pd
import json
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from enum import Enum
from datetime import datetime
class AssemblyType(Enum):
"""Types of assemblies."""
STRUCTURAL = "structural"
ARCHITECTURAL = "architectural"
MECHANICAL = "mechanical"
ELECTRICAL = "electrical"
SITEWORK = "sitework"
GENERAL = "general"
@dataclass
class AssemblyItem:
"""Single item in assembly."""
work_item_code: str
description: str
quantity_per_unit: float # Quantity per assembly unit
unit: str
unit_cost: float
total_cost: float
notes: str = ""
@dataclass
class Assembly:
"""Complete assembly definition."""
assembly_code: str
name: str
description: str
assembly_type: AssemblyType
unit: str # Assembly unit (e.g., "m2", "each", "LF")
items: List[AssemblyItem]
total_cost_per_unit: float
labor_hours_per_unit: float
created_date: datetime
version: int = 1
class CWICRAssemblyBuilder:
"""Build and manage assemblies from CWICR data."""
def __init__(self, cwicr_data: pd.DataFrame):
self.cwicr = cwicr_data
self._index_cwicr()
self._assemblies: Dict[str, Assembly] = {}
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 _get_item_cost(self, code: str) -> Tuple[float, float, str]:
"""Get item unit cost and labor hours."""
if self._cwicr_index is None or code not in self._cwicr_index.index:
return (0, 0, 'unit')
item = self._cwicr_index.loc[code]
labor = float(item.get('labor_cost', 0) or 0)
material = float(item.get('material_cost', 0) or 0)
equipment = float(item.get('equipment_cost', 0) or 0)
labor_hours = float(item.get('labor_norm', item.get('labor_hours', 0)) or 0)
unit = str(item.get('unit', 'unit'))
return (labor + material + equipment, labor_hours, unit)
def create_assembly(self,
assembly_code: str,
name: str,
description: str,
assembly_type: AssemblyType,
unit: str,
items: List[Dict[str, Any]]) -> Assembly:
"""Create new assembly from work items."""
assembly_items = []
total_cost = 0
total_hours = 0
for item_def in items:
code = item_def.get('work_item_code', item_def.get('code'))
qty_per_unit = item_def.get('quantity_per_unit', 1)
notes = item_def.get('notes', '')
unit_cost, labor_hours, item_unit = self._get_item_cost(code)
# Get description from CWICR
if self._cwicr_index is not None and code in self._cwicr_index.index:
desc = str(self._cwicr_index.loc[code].get('description', code))
else:
desc = item_def.get('description', code)
item_total = unit_cost * qty_per_unit
assembly_items.append(AssemblyItem(
work_item_code=code,
description=desc,
quantity_per_unit=qty_per_unit,
unit=item_unit,
unit_cost=round(unit_cost, 2),
total_cost=round(item_total, 2),
notes=notes
))
total_cost += item_total
total_hours += labor_hours * qty_per_unit
assembly = Assembly(
assembly_code=assembly_code,
name=name,
description=description,
assembly_type=assembly_type,
unit=unit,
items=assembly_items,
total_cost_per_unit=round(total_cost, 2),
labor_hours_per_unit=round(total_hours, 2),
created_date=datetime.now(),
version=1
)
self._assemblies[assembly_code] = assembly
return assembly
def apply_assembly(self,
assembly_code: str,
quantity: float,
location_factor: float = 1.0) -> Dict[str, Any]:
"""Apply assembly to get estimate."""
assembly = self._assemblies.get(assembly_code)
if assembly is None:
return {'error': f"Assembly {assembly_code} not found"}
items = []
total_cost = 0
total_hours = 0
for item in assembly.items:
qty = item.quantity_per_unit * quantity
cost = item.total_cost * quantity * location_factor
hours = qty * (item.unit_cost / 50 if item.unit_cost > 0 else 0) # Approximate labor hours
items.append({
'work_item_code': item.work_item_code,
'description': item.description,
'quantity': round(qty, 2),
'unit': item.unit,
'cost': round(cost, 2)
})
total_cost += cost
total_hours += hours
return {
'assembly_code': assembly_code,
'assembly_name': assembly.name,
'quantity': quantity,
'unit': assembly.unit,
'location_factor': location_factor,
'items': items,
'total_cost': round(total_cost, 2),
'total_labor_hours': round(total_hours, 2),
'cost_per_unit': round(total_cost / quantity, 2) if quantity > 0 else 0
}
def get_assembly(self, assembly_code: str) -> Optional[Assembly]:
"""Get assembly by code."""
return self._assemblies.get(assembly_code)
def list_assemblies(self, assembly_type: AssemblyType = None) -> List[Dict[str, Any]]:
"""List all assemblies."""
assemblies = self._assemblies.values()
if assembly_type:
assemblies = [a for a in assemblies if a.assembly_type == assembly_type]
return [
{
'code': a.assembly_code,
'name': a.name,
'type': a.assembly_type.value,
'unit': a.unit,
'cost_per_unit': a.total_cost_per_unit,
'item_count': len(a.items)
}
for a in assemblies
]
def clone_assembly(self,
source_code: str,
new_code: str,
new_name: str = None) -> Optional[Assembly]:
"""Clone existing assembly."""
source = self._assemblies.get(source_code)
if source is None:
return None
new_assembly = Assembly(
assembly_code=new_code,
name=new_name or f"{source.name} (Copy)",
description=source.description,
assembly_type=source.assembly_type,
unit=source.unit,
items=source.items.copy(),
total_cost_per_unit=source.total_cost_per_unit,
labor_hours_per_unit=source.labor_hours_per_unit,
created_date=datetime.now(),
version=1
)
self._assemblies[new_code] = new_assembly
return new_assembly
def compare_assemblies(self,
codes: List[str],
quantity: float = 1) -> pd.DataFrame:
"""Compare multiple assemblies."""
data = []
for code in codes:
assembly = self._assemblies.get(code)
if assembly:
result = self.apply_assembly(code, quantity)
data.append({
'Assembly': assembly.name,
'Code': code,
'Unit': assembly.unit,
'Cost/Unit': assembly.total_cost_per_unit,
'Hours/Unit': assembly.labor_hours_per_unit,
f'Total ({quantity} {assembly.unit})': result['total_cost'],
'Items': len(assembly.items)
})
return pd.DataFrame(data)
def create_standard_assemblies(self):
"""Create standard construction assemblies."""
# Concrete slab assembly
self.create_assembly(
assembly_code="SLAB-100",
name="Concrete Slab 100mm",
description="Standard 100mm concrete slab on grade",
assembly_type=AssemblyType.STRUCTURAL,
unit="m2",
items=[
{'code': 'PREP-001', 'quantity_per_unit': 1.0, 'notes': 'Subgrade preparation'},
{'code': 'GRAVEL-001', 'quantity_per_unit': 0.15, 'notes': '150mm gravel base'},
{'code': 'VAPOR-001', 'quantity_per_unit': 1.1, 'notes': 'Vapor barrier'},
{'code': 'MESH-001', 'quantity_per_unit': 1.1, 'notes': 'Welded wire mesh'},
{'code': 'CONC-001', 'quantity_per_unit': 0.1, 'notes': '100mm concrete'},
{'code': 'FINISH-001', 'quantity_per_unit': 1.0, 'notes': 'Power trowel finish'}
]
)
# Stud wall assembly
self.create_assembly(
assembly_code="WALL-STUD",
name="Metal Stud Wall",
description="Metal stud wall with drywall both sides",
assembly_type=AssemblyType.ARCHITECTURAL,
unit="m2",
items=[
{'code': 'TRACK-001', 'quantity_per_unit': 0.8, 'notes': 'Floor/ceiling track'},
{'code': 'STUD-001', 'quantity_per_unit': 2.5, 'notes': 'Studs @ 400mm OC'},
{'code': 'INSUL-001', 'quantity_per_unit': 1.0, 'notes': 'Batt insulation'},
{'code': 'GYP-001', 'quantity_per_unit': 2.2, 'notes': 'Drywall both sides'},
{'code': 'TAPE-001', 'quantity_per_unit': 2.0, 'notes': 'Tape and mud'}
]
)
def export_assemblies(self, output_path: str) -> str:
"""Export assemblies to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Summary
summary_df = pd.DataFrame([
{
'Code': a.assembly_code,
'Name': a.name,
'Type': a.assembly_type.value,
'Unit': a.unit,
'Cost/Unit': a.total_cost_per_unit,
'Hours/Unit': a.labor_hours_per_unit,
'Items': len(a.items),
'Version': a.version
}
for a in self._assemblies.values()
])
summary_df.to_excel(writer, sheet_name='Assemblies', index=False)
# Details for each assembly
for code, assembly in self._assemblies.items():
if len(code) > 25:
sheet_name = code[:25]
else:
sheet_name = code
detail_df = pd.DataFrame([
{
'Work Item': item.work_item_code,
'Description': item.description,
'Qty/Unit': item.quantity_per_unit,
'Item Unit': item.unit,
'Unit Cost': item.unit_cost,
'Total Cost': item.total_cost,
'Notes': item.notes
}
for item in assembly.items
])
detail_df.to_excel(writer, sheet_name=sheet_name, index=False)
return output_path
def save_library(self, filepath: str):
"""Save assembly library to JSON."""
data = {}
for code, assembly in self._assemblies.items():
data[code] = {
'assembly_code': assembly.assembly_code,
'name': assembly.name,
'description': assembly.description,
'assembly_type': assembly.assembly_type.value,
'unit': assembly.unit,
'items': [
{
'work_item_code': item.work_item_code,
'description': item.description,
'quantity_per_unit': item.quantity_per_unit,
'unit': item.unit,
'notes': item.notes
}
for item in assembly.items
],
'version': assembly.version
}
with open(filepath, 'w') as f:
json.dump(data, f, indent=2)
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 · 438 lines · 28 tokens per session scan A 149c35fffccf
cwicr-assembly-builder is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (310 stars, last pushed 20d ago), licensed MIT. It adds 28 tokens to every session and 3,337 once invoked, about $0.0001 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
catchup
Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
work
Execute Elixir/Phoenix plan tasks with progress tracking. Use after /phx:plan to implement features with mix compile and mix test verification after each step, or --continue to resume interrupted work.
phx-deps-update
Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
proposal-writer
Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service…