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 bim-validation-pipelinegit 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/bim-validation-pipeline)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-pipeline"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-pipeline/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/bim-validation-pipeline"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-pipeline.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00036 | $0.04307 |
| Opus 5 | $0.00018 | $0.02153 |
| Sonnet 5 | $0.00007 | $0.00861 |
| Haiku 4.5 | $0.00004 | $0.00431 |
Grade A, and why
bim-validation-pipeline 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 9d 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:
- bim-validation-pipeline — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 629 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BIM Validation Pipeline
Overview
Based on DDC methodology (Chapter 4.3), this skill provides automated BIM data validation pipelines. Validate BIM models against Information Delivery Specification (IDS), Level of Development (LOD) requirements, and project standards.
Book Reference: "Автоматический ETL конвейер для валидации данных" / "Automated ETL Pipeline for Data Validation"
"Автоматизированная валидация BIM-данных позволяет выявлять ошибки на ранних стадиях и обеспечивать соответствие требованиям BEP." — DDC Book, Chapter 4.3
Quick Start
import ifcopenshell
import pandas as pd
# Load IFC model
ifc_model = ifcopenshell.open("model.ifc")
# Quick validation checks
walls = ifc_model.by_type("IfcWall")
print(f"Total walls: {len(walls)}")
# Check for required properties
issues = []
for wall in walls:
# Check if wall has material
if not wall.HasAssociations:
issues.append(f"Wall {wall.GlobalId}: No material assigned")
print(f"Issues found: {len(issues)}")
BIM Validation Framework
Core Validator Class
import ifcopenshell
import ifcopenshell.util.element as element_util
import pandas as pd
from dataclasses import dataclass
from typing import List, Dict, Optional
from enum import Enum
class Severity(Enum):
ERROR = "error"
WARNING = "warning"
INFO = "info"
@dataclass
class ValidationIssue:
element_id: str
element_type: str
rule_id: str
severity: Severity
message: str
location: Optional[str] = None
class BIMValidator:
"""Comprehensive BIM model validator"""
def __init__(self, ifc_path: str):
self.model = ifcopenshell.open(ifc_path)
self.issues: List[ValidationIssue] = []
self.stats = {}
def validate_all(self):
"""Run all validation checks"""
self.validate_geometry()
self.validate_properties()
self.validate_relationships()
self.validate_naming()
self.validate_classification()
return self.get_report()
def validate_geometry(self):
"""Check geometry validity"""
elements_with_geometry = [
e for e in self.model.by_type("IfcProduct")
if e.Representation
]
for element in elements_with_geometry:
# Check for zero volume
try:
settings = ifcopenshell.geom.settings()
shape = ifcopenshell.geom.create_shape(settings, element)
# Volume check would go here
except:
self.issues.append(ValidationIssue(
element_id=element.GlobalId,
element_type=element.is_a(),
rule_id="GEO-001",
severity=Severity.ERROR,
message="Invalid or missing geometry"
))
self.stats['elements_with_geometry'] = len(elements_with_geometry)
def validate_properties(self, required_psets: Dict[str, List[str]] = None):
"""Check required property sets and properties"""
if required_psets is None:
required_psets = {
'IfcWall': ['Pset_WallCommon', 'BaseQuantities'],
'IfcSlab': ['Pset_SlabCommon', 'BaseQuantities'],
'IfcColumn': ['Pset_ColumnCommon', 'BaseQuantities'],
'IfcBeam': ['Pset_BeamCommon', 'BaseQuantities']
}
for ifc_type, psets in required_psets.items():
elements = self.model.by_type(ifc_type)
for element in elements:
element_psets = element_util.get_psets(element)
for required_pset in psets:
if required_pset not in element_psets:
self.issues.append(ValidationIssue(
element_id=element.GlobalId,
element_type=ifc_type,
rule_id="PROP-001",
severity=Severity.WARNING,
message=f"Missing PropertySet: {required_pset}"
))
def validate_relationships(self):
"""Check spatial containment and relationships"""
products = self.model.by_type("IfcProduct")
for product in products:
# Check spatial containment
if hasattr(product, 'ContainedInStructure'):
if not product.ContainedInStructure:
self.issues.append(ValidationIssue(
element_id=product.GlobalId,
element_type=product.is_a(),
rule_id="REL-001",
severity=Severity.WARNING,
message="Element not assigned to building storey"
))
# Check material assignment
if hasattr(product, 'HasAssociations'):
has_material = any(
rel.is_a('IfcRelAssociatesMaterial')
for rel in (product.HasAssociations or [])
)
if not has_material and product.is_a() in ['IfcWall', 'IfcSlab', 'IfcColumn']:
self.issues.append(ValidationIssue(
element_id=product.GlobalId,
element_type=product.is_a(),
rule_id="MAT-001",
severity=Severity.WARNING,
message="No material assigned"
))
def validate_naming(self, patterns: Dict[str, str] = None):
"""Validate element naming conventions"""
import re
if patterns is None:
patterns = {
'IfcBuildingStorey': r'^(Level|L|Floor|Уровень)\s*[-]?\d+',
'IfcWall': r'^W[-_]?\d{3,}|^Wall[-_]',
'IfcColumn': r'^C[-_]?\d{3,}|^Column[-_]',
'IfcSpace': r'^Room[-_]|^Space[-_]'
}
for ifc_type, pattern in patterns.items():
elements = self.model.by_type(ifc_type)
for element in elements:
name = element.Name or ""
if not re.match(pattern, name, re.IGNORECASE):
self.issues.append(ValidationIssue(
element_id=element.GlobalId,
element_type=ifc_type,
rule_id="NAME-001",
severity=Severity.INFO,
message=f"Name '{name}' doesn't match convention"
))
def validate_classification(self, required_systems: List[str] = None):
"""Check classification system assignments"""
if required_systems is None:
required_systems = ['Uniclass', 'OmniClass', 'Uniformat']
elements = self.model.by_type("IfcProduct")
for element in elements:
if hasattr(element, 'HasAssociations'):
has_classification = any(
rel.is_a('IfcRelAssociatesClassification')
for rel in (element.HasAssociations or [])
)
if not has_classification:
self.issues.append(ValidationIssue(
element_id=element.GlobalId,
element_type=element.is_a(),
rule_id="CLASS-001",
severity=Severity.INFO,
message="No classification assigned"
))
def get_report(self):
"""Generate validation report"""
by_severity = {s: [] for s in Severity}
by_type = {}
by_rule = {}
for issue in self.issues:
by_severity[issue.severity].append(issue)
if issue.element_type not in by_type:
by_type[issue.element_type] = []
by_type[issue.element_type].append(issue)
if issue.rule_id not in by_rule:
by_rule[issue.rule_id] = []
by_rule[issue.rule_id].append(issue)
return {
'total_issues': len(self.issues),
'errors': len(by_severity[Severity.ERROR]),
'warnings': len(by_severity[Severity.WARNING]),
'info': len(by_severity[Severity.INFO]),
'by_type': {k: len(v) for k, v in by_type.items()},
'by_rule': {k: len(v) for k, v in by_rule.items()},
'issues': self.issues,
'stats': self.stats
}
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.
- 9d ago First seen · 629 lines · 36 tokens per session scan A 5f08b3837456
bim-validation-pipeline 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 36 tokens to every session and 4,307 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 2026-09-03.
Other skills, from other repositories
audit
Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.
investigate
Investigate bugs and errors in Elixir/Phoenix — root-cause analysis for crashes, exceptions, stack traces, test failures. Use --parallel for deep 4-track investigation.
narrow-bare-rescue
Narrow bare rescue in Elixir so real errors like KeyError and typos propagate instead of being swallowed. Use to audit rescues and refactor error handling.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.
phx-investigate
Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.