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 batch-cad-convertergit 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/batch-cad-converter)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/batch-cad-converter"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/batch-cad-converter/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/batch-cad-converter"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/batch-cad-converter.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 | $0.00036 | $0.02886 |
| Opus 5 | $0.00018 | $0.01443 |
| Sonnet 5 | $0.00007 | $0.00577 |
| Haiku 4.5 | $0.00004 | $0.00289 |
Grade A, and why
batch-cad-converter 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 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.
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, timeout=3600) Copies of this mod
1 near-identical copy found in the catalogue:
- batch-cad-converter — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch CAD/BIM Converter
Business Case
Problem Statement
Large projects and archives contain hundreds or thousands of CAD/BIM files:
- Manual conversion is tedious and error-prone
- Different formats require different converters
- Progress tracking is needed for long operations
- Error handling is critical for large batches
Solution
Unified batch converter handling all supported formats with progress tracking, error recovery, and consolidated reporting.
Business Value
- Multi-format - Revit, IFC, DWG, DGN in one workflow
- Error recovery - Continue on failures
- Progress tracking - Monitor large batches
- Reporting - Consolidated conversion results
Python Implementation
import subprocess
from pathlib import Path
from typing import List, Optional, Dict, Any, Callable
from dataclasses import dataclass, field
from datetime import datetime
import time
import json
from enum import Enum
from concurrent.futures import ThreadPoolExecutor, as_completed
class CADFormat(Enum):
"""Supported CAD/BIM formats."""
REVIT = (".rvt", ".rfa")
IFC = (".ifc",)
DWG = (".dwg",)
DGN = (".dgn",)
class ConversionStatus(Enum):
"""Status of conversion operation."""
PENDING = "pending"
CONVERTING = "converting"
SUCCESS = "success"
FAILED = "failed"
SKIPPED = "skipped"
@dataclass
class ConversionResult:
"""Result of single file conversion."""
input_file: str
output_file: Optional[str]
format: str
status: ConversionStatus
start_time: datetime
end_time: Optional[datetime]
duration_seconds: float
error_message: Optional[str] = None
file_size_kb: float = 0
@dataclass
class BatchResult:
"""Result of batch conversion."""
total_files: int
successful: int
failed: int
skipped: int
total_duration: float
results: List[ConversionResult]
start_time: datetime
end_time: datetime
class BatchCADConverter:
"""Batch convert multiple CAD/BIM files."""
# Default converter paths
DEFAULT_CONVERTERS = {
'revit': 'RvtExporter.exe',
'ifc': 'IfcExporter.exe',
'dwg': 'DwgExporter.exe',
'dgn': 'DgnExporter.exe'
}
def __init__(self, converter_dir: str = ".",
converters: Dict[str, str] = None):
self.converter_dir = Path(converter_dir)
self.converters = converters or self.DEFAULT_CONVERTERS
self.results: List[ConversionResult] = []
self.progress_callback: Optional[Callable] = None
def set_progress_callback(self, callback: Callable[[int, int, str], None]):
"""Set callback for progress updates."""
self.progress_callback = callback
def _get_format(self, file_path: Path) -> Optional[str]:
"""Detect CAD format from extension."""
ext = file_path.suffix.lower()
for format_name, extensions in [
('revit', ('.rvt', '.rfa')),
('ifc', ('.ifc',)),
('dwg', ('.dwg',)),
('dgn', ('.dgn',))
]:
if ext in extensions:
return format_name
return None
def _get_converter(self, format_name: str) -> Optional[Path]:
"""Get converter path for format."""
if format_name not in self.converters:
return None
converter = self.converter_dir / self.converters[format_name]
if converter.exists():
return converter
# Try in system PATH
return Path(self.converters[format_name])
def convert_file(self, input_file: str,
output_dir: Optional[str] = None,
options: List[str] = None) -> ConversionResult:
"""Convert single file."""
input_path = Path(input_file)
start_time = datetime.now()
# Detect format
format_name = self._get_format(input_path)
if not format_name:
return ConversionResult(
input_file=input_file,
output_file=None,
format='unknown',
status=ConversionStatus.SKIPPED,
start_time=start_time,
end_time=datetime.now(),
duration_seconds=0,
error_message="Unsupported format"
)
# Get converter
converter = self._get_converter(format_name)
if not converter:
return ConversionResult(
input_file=input_file,
output_file=None,
format=format_name,
status=ConversionStatus.FAILED,
start_time=start_time,
end_time=datetime.now(),
duration_seconds=0,
error_message=f"Converter not found for {format_name}"
)
# Build command
cmd = [str(converter), str(input_path)]
if options:
cmd.extend(options)
# Execute
try:
result = subprocess.run(cmd, capture_output=True, text=True, timeout=3600)
end_time = datetime.now()
duration = (end_time - start_time).total_seconds()
# Determine output file
output_file = input_path.with_suffix('.xlsx')
if output_dir:
output_file = Path(output_dir) / output_file.name
if result.returncode == 0 and output_file.exists():
return ConversionResult(
input_file=input_file,
output_file=str(output_file),
format=format_name,
status=ConversionStatus.SUCCESS,
start_time=start_time,
end_time=end_time,
duration_seconds=duration,
file_size_kb=output_file.stat().st_size / 1024
)
else:
return ConversionResult(
input_file=input_file,
output_file=None,
format=format_name,
status=ConversionStatus.FAILED,
start_time=start_time,
end_time=end_time,
duration_seconds=duration,
error_message=result.stderr or "Conversion failed"
)
except subprocess.TimeoutExpired:
return ConversionResult(
input_file=input_file,
output_file=None,
format=format_name,
status=ConversionStatus.FAILED,
start_time=start_time,
end_time=datetime.now(),
duration_seconds=3600,
error_message="Timeout exceeded (1 hour)"
)
except Exception as e:
return ConversionResult(
input_file=input_file,
output_file=None,
format=format_name,
status=ConversionStatus.FAILED,
start_time=start_time,
end_time=datetime.now(),
duration_seconds=0,
error_message=str(e)
)
def batch_convert(self, input_folder: str,
output_folder: Optional[str] = None,
include_subfolders: bool = True,
formats: List[str] = None,
options: Dict[str, List[str]] = None,
parallel: bool = False,
max_workers: int = 4) -> BatchResult:
"""Convert all files in folder."""
start_time = datetime.now()
input_path = Path(input_folder)
# Find all supported files
files = []
pattern = "**/*" if include_subfolders else "*"
for ext in ['.rvt', '.rfa', '.ifc', '.dwg', '.dgn']:
files.extend(input_path.glob(f"{pattern}{ext}"))
# Filter by format if specified
if formats:
files = [f for f in files if self._get_format(f) in formats]
total_files = len(files)
self.results = []
# Create output directory
if output_folder:
Path(output_folder).mkdir(parents=True, exist_ok=True)
# Process files
if parallel and total_files > 1:
self._convert_parallel(files, output_folder, options, max_workers)
else:
self._convert_sequential(files, output_folder, options)
end_time = datetime.now()
# Calculate statistics
successful = sum(1 for r in self.results if r.status == ConversionStatus.SUCCESS)
failed = sum(1 for r in self.results if r.status == ConversionStatus.FAILED)
skipped = sum(1 for r in self.results if r.status == ConversionStatus.SKIPPED)
return BatchResult(
total_files=total_files,
successful=successful,
failed=failed,
skipped=skipped,
total_duration=(end_time - start_time).total_seconds(),
results=self.results,
start_time=start_time,
end_time=end_time
)
def _convert_sequential(self, files: List[Path],
output_folder: Optional[str],
options: Dict[str, List[str]]):
"""Convert files sequentially."""
total = len(files)
for i, file_path in enumerate(files, 1):
if self.progress_callback:
self.progress_callback(i, total, str(file_path))
format_name = self._get_format(file_path)
format_options = options.get(format_name, []) if options else []
result = self.convert_file(str(file_path), output_folder, format_options)
self.results.append(result)
status_symbol = "✓" if result.status == ConversionStatus.SUCCESS else "✗"
print(f"[{i}/{total}] {status_symbol} {file_path.name}")
def _convert_parallel(self, files: List[Path],
output_folder: Optional[str],
options: Dict[str, List[str]],
max_workers: int):
"""Convert files in parallel."""
total = len(files)
with ThreadPoolExecutor(max_workers=max_workers) as executor:
futures = {}
for file_path in files:
format_name = self._get_format(file_path)
format_options = options.get(format_name, []) if options else []
future = executor.submit(self.convert_file, str(file_path), output_folder, format_options)
futures[future] = file_path
completed = 0
for future in as_completed(futures):
completed += 1
result = future.result()
self.results.append(result)
if self.progress_callback:
self.progress_callback(completed, total, str(futures[future]))
def generate_report(self, batch_result: BatchResult,
output_path: str = None) -> str:
"""Generate conversion report."""
report = {
'summary': {
'total_files': batch_result.total_files,
'successful': batch_result.successful,
'failed': batch_result.failed,
'skipped': batch_result.skipped,
'success_rate': round(batch_result.successful / batch_result.total_files * 100, 1) if batch_result.total_files > 0 else 0,
'total_duration_seconds': round(batch_result.total_duration, 2),
'start_time': batch_result.start_time.isoformat(),
'end_time': batch_result.end_time.isoformat()
},
'results': [
{
'input': r.input_file,
'output': r.output_file,
'format': r.format,
'status': r.status.value,
'duration': round(r.duration_seconds, 2),
'error': r.error_message
}
for r in batch_result.results
]
}
report_json = json.dumps(report, indent=2)
if output_path:
with open(output_path, 'w') as f:
f.write(report_json)
return report_json
# Progress callback example
def print_progress(current: int, total: int, file_name: str):
"""Print progress to console."""
percent = current / total * 100
print(f"Progress: {current}/{total} ({percent:.1f}%) - {file_name}")
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 · 429 lines · 36 tokens per session scan A 675c582c1c7a
batch-cad-converter 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 36 tokens to every session and 2,886 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.
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.
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.