bim-validation-report

bim-validation-report is a skill for Claude Code, Codex from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction. It costs 23 tokens per session (3,152 once invoked), scanned A, original, MIT.

A tool for checking building information models (BIM), digital building models that contain design and construction data, against defined rules and standards. It creates reports showing data-quality and compliance results.

In plain words
What is it for?
Use it to validate BIM models, check required fields and project rules, and produce reports that group issues as errors, warnings, or information.
Why use it?
It helps find missing properties, invalid data, incomplete information, and standards violations before they cause project problems or require manual checking.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: built for openclaw.

Good fit Use it to validate BIM models, check required fields and project rules, and produce reports that group issues as errors, warnings, or information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report
Install

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.

Any agent
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill bim-validation-report
Clone the repo
git clone --depth 1 https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bim-validation-report

README.md
[![agentmods](https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report/github.svg)](https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report)
Your own site
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report/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.

agentmods 80×15 button for bim-validation-report

Your own site · 80×15
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/bim-validation-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,152 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.03152
Opus 5 $0.00012 $0.01576
Sonnet 5 $0.00005 $0.00630
Haiku 4.5 $0.00002 $0.00315

Measured 11d ago against content hash d6b9f7078d7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

bim-validation-report 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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

1_DDC_Toolkit/BIM-Analysis/bim-validation-report/SKILL.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BIM Validation Report Generator

Business Case

Problem Statement

BIM models often have quality issues:

  • Missing required properties
  • Invalid or inconsistent data
  • Non-compliant with project standards
  • Incomplete model information

Solution

Automated BIM validation system that checks models against configurable rules and generates detailed compliance reports.

Business Value

  • Quality assurance - Catch issues early
  • Standards compliance - Meet project requirements
  • Automation - Reduce manual QC effort
  • Transparency - Clear validation results

Technical Implementation

import pandas as pd
from datetime import datetime
from typing import Dict, Any, List, Optional, Callable
from dataclasses import dataclass, field
from enum import Enum


class ValidationSeverity(Enum):
    """Validation issue severity."""
    ERROR = "error"
    WARNING = "warning"
    INFO = "info"


class ValidationStatus(Enum):
    """Overall validation status."""
    PASSED = "passed"
    PASSED_WITH_WARNINGS = "passed_with_warnings"
    FAILED = "failed"


class RuleCategory(Enum):
    """Validation rule categories."""
    REQUIRED_PROPERTIES = "required_properties"
    DATA_FORMAT = "data_format"
    NAMING_CONVENTION = "naming_convention"
    GEOMETRIC = "geometric"
    CLASSIFICATION = "classification"
    RELATIONSHIPS = "relationships"


@dataclass
class ValidationRule:
    """Single validation rule."""
    rule_id: str
    name: str
    category: RuleCategory
    description: str
    severity: ValidationSeverity
    check_function: Callable
    applicable_categories: List[str] = field(default_factory=list)
    enabled: bool = True


@dataclass
class ValidationIssue:
    """Single validation issue."""
    issue_id: str
    rule_id: str
    rule_name: str
    element_id: str
    element_name: str
    element_category: str
    severity: ValidationSeverity
    message: str
    details: Dict[str, Any] = field(default_factory=dict)

    def to_dict(self) -> Dict[str, Any]:
        return {
            'issue_id': self.issue_id,
            'rule_id': self.rule_id,
            'rule_name': self.rule_name,
            'element_id': self.element_id,
            'element_name': self.element_name,
            'element_category': self.element_category,
            'severity': self.severity.value,
            'message': self.message
        }


@dataclass
class ValidationReport:
    """Complete validation report."""
    project_name: str
    model_name: str
    validated_at: datetime
    status: ValidationStatus
    total_elements: int
    elements_with_issues: int
    issues: List[ValidationIssue]
    rules_checked: int
    summary_by_severity: Dict[str, int]
    summary_by_category: Dict[str, int]


class BIMValidationEngine:
    """BIM model validation engine."""

    def __init__(self, project_name: str, model_name: str):
        self.project_name = project_name
        self.model_name = model_name
        self.rules: List[ValidationRule] = []
        self.issues: List[ValidationIssue] = []
        self._issue_counter = 0

        # Load default rules
        self._load_default_rules()

    def _load_default_rules(self):
        """Load standard validation rules."""

        # Required properties rules
        self.add_rule(ValidationRule(
            rule_id="REQ-001",
            name="Element Name Required",
            category=RuleCategory.REQUIRED_PROPERTIES,
            description="All elements must have a name",
            severity=ValidationSeverity.ERROR,
            check_function=lambda e: bool(e.get('name'))
        ))

        self.add_rule(ValidationRule(
            rule_id="REQ-002",
            name="Level Assignment Required",
            category=RuleCategory.REQUIRED_PROPERTIES,
            description="Elements must be assigned to a level",
            severity=ValidationSeverity.WARNING,
            check_function=lambda e: bool(e.get('level')),
            applicable_categories=["Walls", "Floors", "Doors", "Windows"]
        ))

        self.add_rule(ValidationRule(
            rule_id="REQ-003",
            name="Material Required",
            category=RuleCategory.REQUIRED_PROPERTIES,
            description="Structural elements must have material defined",
            severity=ValidationSeverity.ERROR,
            check_function=lambda e: bool(e.get('material')),
            applicable_categories=["Structural Columns", "Structural Framing", "Floors"]
        ))

        # Naming convention rules
        self.add_rule(ValidationRule(
            rule_id="NAM-001",
            name="No Special Characters",
            category=RuleCategory.NAMING_CONVENTION,
            description="Names should not contain special characters",
            severity=ValidationSeverity.WARNING,
            check_function=self._check_no_special_chars
        ))

        self.add_rule(ValidationRule(
            rule_id="NAM-002",
            name="Name Length Check",
            category=RuleCategory.NAMING_CONVENTION,
            description="Names should be between 3 and 100 characters",
            severity=ValidationSeverity.INFO,
            check_function=lambda e: 3 <= len(e.get('name', '')) <= 100
        ))

        # Classification rules
        self.add_rule(ValidationRule(
            rule_id="CLS-001",
            name="Classification Code Present",
            category=RuleCategory.CLASSIFICATION,
            description="Elements should have classification code",
            severity=ValidationSeverity.WARNING,
            check_function=lambda e: bool(e.get('classification_code') or e.get('uniformat'))
        ))

        # Geometric rules
        self.add_rule(ValidationRule(
            rule_id="GEO-001",
            name="Non-Zero Volume",
            category=RuleCategory.GEOMETRIC,
            description="3D elements must have non-zero volume",
            severity=ValidationSeverity.ERROR,
            check_function=lambda e: float(e.get('volume', 0)) > 0,
            applicable_categories=["Walls", "Floors", "Structural Columns", "Structural Framing"]
        ))

        self.add_rule(ValidationRule(
            rule_id="GEO-002",
            name="Valid Bounding Box",
            category=RuleCategory.GEOMETRIC,
            description="Elements must have valid bounding box",
            severity=ValidationSeverity.ERROR,
            check_function=self._check_valid_bbox
        ))

    def _check_no_special_chars(self, element: Dict[str, Any]) -> bool:
        """Check name for special characters."""
        import re
        name = element.get('name', '')
        return bool(re.match(r'^[\w\s\-\.]+$', name))

    def _check_valid_bbox(self, element: Dict[str, Any]) -> bool:
        """Check for valid bounding box."""
        try:
            min_x = float(element.get('min_x', 0))
            max_x = float(element.get('max_x', 0))
            min_y = float(element.get('min_y', 0))
            max_y = float(element.get('max_y', 0))
            min_z = float(element.get('min_z', 0))
            max_z = float(element.get('max_z', 0))
            return max_x > min_x and max_y > min_y and max_z > min_z
        except (ValueError, TypeError):
            return False

    def add_rule(self, rule: ValidationRule):
        """Add validation rule."""
        self.rules.append(rule)

    def add_custom_rule(self, rule_id: str, name: str, category: RuleCategory,
                       check_function: Callable, severity: ValidationSeverity = ValidationSeverity.WARNING,
                       description: str = "", categories: List[str] = None):
        """Add custom validation rule."""
        rule = ValidationRule(
            rule_id=rule_id,
            name=name,
            category=category,
            description=description,
            severity=severity,
            check_function=check_function,
            applicable_categories=categories or []
        )
        self.add_rule(rule)

    def validate_element(self, element: Dict[str, Any]) -> List[ValidationIssue]:
        """Validate single element against all rules."""
        issues = []
        element_category = element.get('category', '')

        for rule in self.rules:
            if not rule.enabled:
                continue

            # Check if rule applies to this category
            if rule.applicable_categories and element_category not in rule.applicable_categories:
                continue

            try:
                passed = rule.check_function(element)
                if not passed:
                    self._issue_counter += 1
                    issue = ValidationIssue(
                        issue_id=f"ISS-{self._issue_counter:05d}",
                        rule_id=rule.rule_id,
                        rule_name=rule.name,
                        element_id=str(element.get('element_id', '')),
                        element_name=str(element.get('name', '')),
                        element_category=element_category,
                        severity=rule.severity,
                        message=rule.description
                    )
                    issues.append(issue)
            except Exception as e:
                # Rule check failed
                self._issue_counter += 1
                issue = ValidationIssue(
                    issue_id=f"ISS-{self._issue_counter:05d}",
                    rule_id=rule.rule_id,
                    rule_name=rule.name,
                    element_id=str(element.get('element_id', '')),
                    element_name=str(element.get('name', '')),
                    element_category=element_category,
                    severity=ValidationSeverity.ERROR,
                    message=f"Rule check error: {str(e)}"
                )
                issues.append(issue)

        return issues

    def validate_model(self, elements_df: pd.DataFrame) -> ValidationReport:
        """Validate entire BIM model."""
        self.issues = []
        elements_with_issues = set()

        for _, row in elements_df.iterrows():
            element = row.to_dict()
            element_issues = self.validate_element(element)

            if element_issues:
                elements_with_issues.add(element.get('element_id'))
                self.issues.extend(element_issues)

        # Calculate summaries
        summary_by_severity = {
            'error': sum(1 for i in self.issues if i.severity == ValidationSeverity.ERROR),
            'warning': sum(1 for i in self.issues if i.severity == ValidationSeverity.WARNING),
            'info': sum(1 for i in self.issues if i.severity == ValidationSeverity.INFO)
        }

        summary_by_category = {}
        for issue in self.issues:
            cat = issue.element_category
            summary_by_category[cat] = summary_by_category.get(cat, 0) + 1

        # Determine overall status
        if summary_by_severity['error'] > 0:
            status = ValidationStatus.FAILED
        elif summary_by_severity['warning'] > 0:
            status = ValidationStatus.PASSED_WITH_WARNINGS
        else:
            status = ValidationStatus.PASSED

        return ValidationReport(
            project_name=self.project_name,
            model_name=self.model_name,
            validated_at=datetime.now(),
            status=status,
            total_elements=len(elements_df),
            elements_with_issues=len(elements_with_issues),
            issues=self.issues,
            rules_checked=len([r for r in self.rules if r.enabled]),
            summary_by_severity=summary_by_severity,
            summary_by_category=summary_by_category
        )

    def export_report(self, report: ValidationReport, output_path: str):
        """Export validation report to Excel."""
        with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
            # Summary sheet
            summary_data = {
                'Metric': ['Project', 'Model', 'Validated At', 'Status',
                          'Total Elements', 'Elements with Issues', 'Rules Checked',
                          'Errors', 'Warnings', 'Info'],
                'Value': [report.project_name, report.model_name,
                         report.validated_at.isoformat(), report.status.value,
                         report.total_elements, report.elements_with_issues,
                         report.rules_checked, report.summary_by_severity['error'],
                         report.summary_by_severity['warning'], report.summary_by_severity['info']]
            }
            pd.DataFrame(summary_data).to_excel(writer, sheet_name='Summary', index=False)

            # Issues sheet
            issues_df = pd.DataFrame([i.to_dict() for i in report.issues])
            if not issues_df.empty:
                issues_df.to_excel(writer, sheet_name='Issues', index=False)

            # By Category sheet
            cat_df = pd.DataFrame([
                {'Category': k, 'Issue Count': v}
                for k, v in report.summary_by_category.items()
            ])
            if not cat_df.empty:
                cat_df.to_excel(writer, sheet_name='By Category', index=False)

        return output_path


def generate_validation_report(elements_df: pd.DataFrame,
                               project_name: str,
                               model_name: str,
                               output_path: str = None) -> ValidationReport:
    """Quick function to generate validation report."""
    engine = BIMValidationEngine(project_name, model_name)
    report = engine.validate_model(elements_df)

    if output_path:
        engine.export_report(report, output_path)

    return report

Read the full file on GitHub · 440 lines

Files

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.

Changes

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.

  1. 11d ago First seen · 440 lines · 23 tokens per session scan A d6b9f7078d7e

Subscribe to this mod's changes

bim-validation-report is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (308 stars, last pushed 20d ago), licensed MIT. It adds 23 tokens to every session and 3,152 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.

Related

Other skills, from other repositories

phx-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.

oliver-kriska/claude-elixir-phoenix · 43 tokens

codex-loop

Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.

oliver-kriska/claude-elixir-phoenix · 52 tokens

verify

Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.

oliver-kriska/claude-elixir-phoenix · 33 tokens

codex-ab

Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.

oliver-kriska/claude-elixir-phoenix · 60 tokens

mix-compression

Reduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.

oliver-kriska/claude-elixir-phoenix · 48 tokens

testing

Write or repair Elixir tests with ExUnit, sandbox isolation, async reliability, Mox, ExMachina, and LiveViewTest. Use for test files, test setup, or failing/flaky tests. NOT for investigating an application bug outside the test suite.

oliver-kriska/claude-elixir-phoenix · 55 tokens