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 rvt-to-ifcgit 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/rvt-to-ifc)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/rvt-to-ifc"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/rvt-to-ifc/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/rvt-to-ifc"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/rvt-to-ifc.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 | $0.00032 | $0.02420 |
| Opus 5 | $0.00016 | $0.01210 |
| Sonnet 5 | $0.00006 | $0.00484 |
| Haiku 4.5 | $0.00003 | $0.00242 |
Grade A, and why
rvt-to-ifc scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run(cmd, capture_output=True, text=True) Copies of this mod
1 near-identical copy found in the catalogue:
- rvt-to-ifc — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 328 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RVT to IFC Conversion
Note: RVT is the file format. IFC is an open standard by buildingSMART International.
Business Case
Problem Statement
IFC is the open BIM standard for interoperability, but:
- Native Revit IFC export requires Autodesk license
- Export settings significantly affect data quality
- Batch processing is manual and time-consuming
Solution
RVT2IFCconverter.exe converts Revit files to IFC offline, without licenses, with full control over export settings.
Business Value
- No license required - Works without Autodesk software
- Multiple IFC versions - IFC2x3, IFC4, IFC4.3 support
- Batch processing - Convert thousands of files
- Consistent quality - Standardized export settings
Technical Implementation
CLI Syntax
RVT2IFCconverter.exe <input.rvt> [<output.ifc>] [preset=<name>] [config="..."]
IFC Versions
| Version | Use Case |
|---|---|
| IFC2x3 | Legacy compatibility, most software |
| IFC4 | Enhanced properties, modern BIM |
| IFC4.3 | Infrastructure, latest standard |
Export Presets
| Preset | Description |
|---|---|
standard |
Default balanced export |
extended |
Maximum detail and properties |
custom |
User-defined configuration |
Examples
# Standard IFC export
RVT2IFCconverter.exe "C:\Projects\Building.rvt"
# IFC4 with extended settings
RVT2IFCconverter.exe "C:\Projects\Building.rvt" preset=extended
# Custom output path
RVT2IFCconverter.exe "C:\Projects\Building.rvt" "D:\Export\model.ifc"
# Custom configuration
RVT2IFCconverter.exe "C:\Projects\Building.rvt" config="ExportBaseQuantities=true; SitePlacement=Shared"
Python Integration
import subprocess
from pathlib import Path
from typing import List, Optional, Dict, Any
from dataclasses import dataclass
from enum import Enum
class IFCVersion(Enum):
"""IFC schema versions."""
IFC2X3 = "IFC2x3"
IFC4 = "IFC4"
IFC4X3 = "IFC4x3"
class ExportPreset(Enum):
"""Export presets."""
STANDARD = "standard"
EXTENDED = "extended"
CUSTOM = "custom"
@dataclass
class IFCExportConfig:
"""IFC export configuration."""
ifc_version: IFCVersion = IFCVersion.IFC4
export_base_quantities: bool = True
site_placement: str = "Shared"
split_walls_and_columns: bool = False
include_steel_elements: bool = True
export_2d_elements: bool = False
export_linked_files: bool = False
export_rooms: bool = True
export_schedules: bool = True
def to_config_string(self) -> str:
"""Convert to CLI config string."""
parts = [
f"ExportBaseQuantities={str(self.export_base_quantities).lower()}",
f"SitePlacement={self.site_placement}",
f"SplitWallsAndColumns={str(self.split_walls_and_columns).lower()}",
f"IncludeSteelElements={str(self.include_steel_elements).lower()}",
f"Export2DElements={str(self.export_2d_elements).lower()}",
f"ExportLinkedFiles={str(self.export_linked_files).lower()}",
f"ExportRooms={str(self.export_rooms).lower()}"
]
return "; ".join(parts)
class RevitToIFCConverter:
"""Convert Revit files to IFC format."""
def __init__(self, converter_path: str = "RVT2IFCconverter.exe"):
self.converter = Path(converter_path)
if not self.converter.exists():
raise FileNotFoundError(f"Converter not found: {converter_path}")
def convert(self, rvt_file: str,
output_path: Optional[str] = None,
preset: ExportPreset = ExportPreset.STANDARD,
config: Optional[IFCExportConfig] = None) -> Path:
"""Convert Revit file to IFC."""
rvt_path = Path(rvt_file)
if not rvt_path.exists():
raise FileNotFoundError(f"Revit file not found: {rvt_file}")
# Build command
cmd = [str(self.converter), str(rvt_path)]
# Add output path if specified
if output_path:
cmd.append(output_path)
# Add preset
cmd.append(f"preset={preset.value}")
# Add custom config if provided
if config:
cmd.append(f'config="{config.to_config_string()}"')
# Execute
result = subprocess.run(cmd, capture_output=True, text=True)
if result.returncode != 0:
raise RuntimeError(f"Conversion failed: {result.stderr}")
# Return output path
if output_path:
return Path(output_path)
return rvt_path.with_suffix('.ifc')
def batch_convert(self, folder: str,
output_folder: Optional[str] = None,
preset: ExportPreset = ExportPreset.STANDARD,
config: Optional[IFCExportConfig] = None) -> List[Dict[str, Any]]:
"""Convert all Revit files in folder."""
folder_path = Path(folder)
results = []
for rvt_file in folder_path.glob("**/*.rvt"):
try:
# Determine output path
if output_folder:
out_dir = Path(output_folder)
out_dir.mkdir(parents=True, exist_ok=True)
output_path = str(out_dir / rvt_file.with_suffix('.ifc').name)
else:
output_path = None
ifc_path = self.convert(str(rvt_file), output_path, preset, config)
results.append({
'input': str(rvt_file),
'output': str(ifc_path),
'status': 'success'
})
print(f"✓ Converted: {rvt_file.name}")
except Exception as e:
results.append({
'input': str(rvt_file),
'output': None,
'status': 'failed',
'error': str(e)
})
print(f"✗ Failed: {rvt_file.name} - {e}")
return results
def validate_output(self, ifc_file: str) -> Dict[str, Any]:
"""Basic validation of generated IFC."""
ifc_path = Path(ifc_file)
if not ifc_path.exists():
return {'valid': False, 'error': 'File not found'}
# Basic file checks
file_size = ifc_path.stat().st_size
if file_size < 1000:
return {'valid': False, 'error': 'File too small'}
# Read header
with open(ifc_file, 'r', errors='ignore') as f:
header = f.read(1000)
# Check IFC format
if 'ISO-10303-21' not in header:
return {'valid': False, 'error': 'Not a valid IFC file'}
# Detect version
version = 'Unknown'
if 'IFC4X3' in header:
version = 'IFC4.3'
elif 'IFC4' in header:
version = 'IFC4'
elif 'IFC2X3' in header:
version = 'IFC2x3'
return {
'valid': True,
'file_size': file_size,
'ifc_version': version
}
class IFCQualityChecker:
"""Check quality of IFC exports."""
def __init__(self, converter: RevitToIFCConverter):
self.converter = converter
def compare_presets(self, rvt_file: str) -> Dict[str, Any]:
"""Compare different export presets."""
results = {}
for preset in [ExportPreset.STANDARD, ExportPreset.EXTENDED]:
try:
output = Path(rvt_file).with_suffix(f'.{preset.value}.ifc')
self.converter.convert(rvt_file, str(output), preset)
validation = self.converter.validate_output(str(output))
results[preset.value] = {
'file_size': validation.get('file_size', 0),
'valid': validation.get('valid', False)
}
except Exception as e:
results[preset.value] = {'error': str(e)}
return results
# Convenience functions
def convert_revit_to_ifc(rvt_file: str,
converter_path: str = "RVT2IFCconverter.exe") -> str:
"""Quick conversion of Revit to IFC."""
converter = RevitToIFCConverter(converter_path)
output = converter.convert(rvt_file)
return str(output)
def batch_convert_to_ifc(folder: str,
converter_path: str = "RVT2IFCconverter.exe") -> List[str]:
"""Batch convert all Revit files to IFC."""
converter = RevitToIFCConverter(converter_path)
results = converter.batch_convert(folder)
return [r['output'] for r in results if r['status'] == 'success']
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 · 328 lines · 32 tokens per session scan A 8b8738335259
rvt-to-ifc 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 32 tokens to every session and 2,420 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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.