ids-checker

ids-checker is a skill for Claude Code, Codex from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction. It costs 21 tokens per session (3,791 once invoked), scanned A, original, MIT.

A checker for Information Delivery Specification (IDS), a document that defines what information a BIM model must contain. It tests model data against required properties, classifications, materials, attributes, and relationships.

In plain words
What is it for?
Use it to verify that BIM models meet defined information requirements and report pass, fail, warning, or not-applicable results.
Why use it?
It replaces slow manual checks and helps detect missing or non-compliant information before delivery.

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 verify that BIM models meet defined information requirements and report pass, fail, warning, or not-applicable results.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/ids-checker
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 ids-checker
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 ids-checker

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/ids-checker"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/ids-checker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,791 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 $0.00021 $0.03791
Opus 5 $0.00010 $0.01895
Sonnet 5 $0.00004 $0.00758
Haiku 4.5 $0.00002 $0.00379

Measured 9d ago against content hash 34234406b877, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

ids-checker 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

2_DDC_Book/4.3-BIM-Validation-Pipeline/ids-checker/SKILL.md · 511 lines

How it starts

The opening of the file, as written. The whole thing — 511 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IDS Checker

Business Case

Problem Statement

BIM data validation challenges:

  • Inconsistent model information
  • Missing required properties
  • Non-compliant data deliveries
  • Manual validation is time-consuming

Solution

Automated IDS (Information Delivery Specification) checking system to validate BIM models against defined requirements.

Technical Implementation

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


class RequirementType(Enum):
    PROPERTY = "property"
    CLASSIFICATION = "classification"
    MATERIAL = "material"
    ATTRIBUTE = "attribute"
    RELATION = "relation"


class Facet(Enum):
    ENTITY = "entity"
    PROPERTY_SET = "property_set"
    PROPERTY = "property"
    CLASSIFICATION = "classification"
    MATERIAL = "material"
    PART_OF = "part_of"


class Cardinality(Enum):
    REQUIRED = "required"
    OPTIONAL = "optional"
    PROHIBITED = "prohibited"


class CheckResult(Enum):
    PASS = "pass"
    FAIL = "fail"
    WARNING = "warning"
    NOT_APPLICABLE = "n/a"


@dataclass
class IDSRequirement:
    req_id: str
    name: str
    description: str
    applicability: Dict[str, Any]  # Which elements this applies to
    requirements: List[Dict[str, Any]]  # What is required
    cardinality: Cardinality = Cardinality.REQUIRED


@dataclass
class ValidationResult:
    element_id: str
    element_type: str
    requirement_id: str
    result: CheckResult
    message: str
    details: Dict[str, Any] = field(default_factory=dict)


@dataclass
class IDSSpecification:
    spec_id: str
    name: str
    version: str
    purpose: str
    requirements: List[IDSRequirement] = field(default_factory=list)


class IDSChecker:
    """Check BIM data against IDS (Information Delivery Specification)."""

    def __init__(self, spec_name: str):
        self.spec_name = spec_name
        self.specifications: Dict[str, IDSSpecification] = {}
        self.results: List[ValidationResult] = []

    def create_specification(self, spec_id: str, name: str,
                             version: str = "1.0", purpose: str = "") -> IDSSpecification:
        """Create new IDS specification."""

        spec = IDSSpecification(
            spec_id=spec_id,
            name=name,
            version=version,
            purpose=purpose
        )
        self.specifications[spec_id] = spec
        return spec

    def add_requirement(self, spec_id: str, requirement: IDSRequirement):
        """Add requirement to specification."""

        if spec_id in self.specifications:
            self.specifications[spec_id].requirements.append(requirement)

    def add_property_requirement(self, spec_id: str, req_id: str, name: str,
                                  entity_type: str, property_set: str,
                                  property_name: str, data_type: str = None,
                                  value_pattern: str = None,
                                  cardinality: Cardinality = Cardinality.REQUIRED):
        """Add property requirement."""

        requirement = IDSRequirement(
            req_id=req_id,
            name=name,
            description=f"Property {property_name} in {property_set}",
            applicability={'entity': entity_type},
            requirements=[{
                'type': RequirementType.PROPERTY.value,
                'property_set': property_set,
                'property_name': property_name,
                'data_type': data_type,
                'value_pattern': value_pattern
            }],
            cardinality=cardinality
        )
        self.add_requirement(spec_id, requirement)

    def add_classification_requirement(self, spec_id: str, req_id: str, name: str,
                                        entity_type: str, system: str,
                                        value_pattern: str = None,
                                        cardinality: Cardinality = Cardinality.REQUIRED):
        """Add classification requirement."""

        requirement = IDSRequirement(
            req_id=req_id,
            name=name,
            description=f"Classification from {system}",
            applicability={'entity': entity_type},
            requirements=[{
                'type': RequirementType.CLASSIFICATION.value,
                'system': system,
                'value_pattern': value_pattern
            }],
            cardinality=cardinality
        )
        self.add_requirement(spec_id, requirement)

    def create_standard_cobie_spec(self) -> str:
        """Create standard COBie specification."""

        spec = self.create_specification(
            "COBIE_BASIC",
            "COBie Basic Requirements",
            "1.0",
            "Basic COBie data requirements for facility handover"
        )

        # Space requirements
        self.add_property_requirement("COBIE_BASIC", "CB-SP-01", "Space Name",
                                       "IfcSpace", "Pset_SpaceCommon", "Name")
        self.add_property_requirement("COBIE_BASIC", "CB-SP-02", "Space Number",
                                       "IfcSpace", "COBie_Space", "SpaceNumber")
        self.add_property_requirement("COBIE_BASIC", "CB-SP-03", "Room Tag",
                                       "IfcSpace", "COBie_Space", "RoomTag")

        # Component requirements
        self.add_property_requirement("COBIE_BASIC", "CB-CO-01", "Component Name",
                                       "IfcElement", "COBie_Component", "Name")
        self.add_property_requirement("COBIE_BASIC", "CB-CO-02", "Component Type",
                                       "IfcElement", "COBie_Component", "TypeName")
        self.add_property_requirement("COBIE_BASIC", "CB-CO-03", "Serial Number",
                                       "IfcElement", "COBie_Component", "SerialNumber",
                                       cardinality=Cardinality.OPTIONAL)

        # Type requirements
        self.add_property_requirement("COBIE_BASIC", "CB-TY-01", "Type Name",
                                       "IfcTypeObject", "COBie_Type", "Name")
        self.add_property_requirement("COBIE_BASIC", "CB-TY-02", "Manufacturer",
                                       "IfcTypeObject", "COBie_Type", "Manufacturer")
        self.add_property_requirement("COBIE_BASIC", "CB-TY-03", "Model Number",
                                       "IfcTypeObject", "COBie_Type", "ModelNumber")

        return "COBIE_BASIC"

    def create_standard_lod_spec(self, lod_level: int = 300) -> str:
        """Create standard LOD specification."""

        spec_id = f"LOD_{lod_level}"
        spec = self.create_specification(
            spec_id,
            f"LOD {lod_level} Requirements",
            "1.0",
            f"Level of Development {lod_level} requirements"
        )

        if lod_level >= 200:
            self.add_property_requirement(spec_id, f"LOD-{lod_level}-01",
                                           "Element must have type",
                                           "IfcElement", "Pset_ElementCommon", "Type")

        if lod_level >= 300:
            self.add_property_requirement(spec_id, f"LOD-{lod_level}-02",
                                           "Element must have dimensions",
                                           "IfcElement", "BaseQuantities", "Length")
            self.add_property_requirement(spec_id, f"LOD-{lod_level}-03",
                                           "Material assignment",
                                           "IfcElement", "Pset_MaterialCommon", "Material")

        if lod_level >= 350:
            self.add_property_requirement(spec_id, f"LOD-{lod_level}-04",
                                           "Fire rating",
                                           "IfcElement", "Pset_ElementCommon", "FireRating",
                                           cardinality=Cardinality.OPTIONAL)
            self.add_classification_requirement(spec_id, f"LOD-{lod_level}-05",
                                                 "Uniformat classification",
                                                 "IfcElement", "Uniformat")

        return spec_id

    def check_element(self, element: Dict[str, Any],
                      spec_id: str) -> List[ValidationResult]:
        """Check single element against specification."""

        results = []

        if spec_id not in self.specifications:
            return results

        spec = self.specifications[spec_id]

        for req in spec.requirements:
            # Check applicability
            if not self._matches_applicability(element, req.applicability):
                continue

            # Check requirements
            for req_def in req.requirements:
                result = self._check_requirement(element, req, req_def)
                results.append(result)

        return results

    def _matches_applicability(self, element: Dict[str, Any],
                                applicability: Dict[str, Any]) -> bool:
        """Check if element matches applicability criteria."""

        entity_filter = applicability.get('entity')
        if entity_filter:
            element_type = element.get('type', '')
            if entity_filter not in element_type:
                return False

        return True

    def _check_requirement(self, element: Dict[str, Any],
                           req: IDSRequirement,
                           req_def: Dict[str, Any]) -> ValidationResult:
        """Check single requirement."""

        req_type = req_def.get('type')

        if req_type == RequirementType.PROPERTY.value:
            return self._check_property_requirement(element, req, req_def)
        elif req_type == RequirementType.CLASSIFICATION.value:
            return self._check_classification_requirement(element, req, req_def)

        return ValidationResult(
            element_id=element.get('id', ''),
            element_type=element.get('type', ''),
            requirement_id=req.req_id,
            result=CheckResult.NOT_APPLICABLE,
            message="Unknown requirement type"
        )

    def _check_property_requirement(self, element: Dict[str, Any],
                                     req: IDSRequirement,
                                     req_def: Dict[str, Any]) -> ValidationResult:
        """Check property requirement."""

        pset_name = req_def.get('property_set')
        prop_name = req_def.get('property_name')
        value_pattern = req_def.get('value_pattern')

        # Get property value
        properties = element.get('properties', {})
        pset = properties.get(pset_name, {})
        value = pset.get(prop_name)

        result = ValidationResult(
            element_id=element.get('id', ''),
            element_type=element.get('type', ''),
            requirement_id=req.req_id,
            result=CheckResult.PASS,
            message="",
            details={'property_set': pset_name, 'property': prop_name, 'value': value}
        )

        # Check if property exists
        if value is None:
            if req.cardinality == Cardinality.REQUIRED:
                result.result = CheckResult.FAIL
                result.message = f"Missing required property: {pset_name}.{prop_name}"
            elif req.cardinality == Cardinality.PROHIBITED:
                result.result = CheckResult.PASS
                result.message = "Prohibited property correctly absent"
            else:
                result.result = CheckResult.WARNING
                result.message = f"Optional property missing: {pset_name}.{prop_name}"
            return result

        # Check if property should not exist
        if req.cardinality == Cardinality.PROHIBITED:
            result.result = CheckResult.FAIL
            result.message = f"Prohibited property exists: {pset_name}.{prop_name}"
            return result

        # Check value pattern
        if value_pattern:
            if not re.match(value_pattern, str(value)):
                result.result = CheckResult.FAIL
                result.message = f"Value '{value}' does not match pattern '{value_pattern}'"
                return result

        result.message = f"Property {prop_name} = {value}"
        return result

    def _check_classification_requirement(self, element: Dict[str, Any],
                                           req: IDSRequirement,
                                           req_def: Dict[str, Any]) -> ValidationResult:
        """Check classification requirement."""

        system = req_def.get('system')
        value_pattern = req_def.get('value_pattern')

        classifications = element.get('classifications', {})
        value = classifications.get(system)

        result = ValidationResult(
            element_id=element.get('id', ''),
            element_type=element.get('type', ''),
            requirement_id=req.req_id,
            result=CheckResult.PASS,
            message="",
            details={'system': system, 'value': value}
        )

        if value is None:
            if req.cardinality == Cardinality.REQUIRED:
                result.result = CheckResult.FAIL
                result.message = f"Missing classification: {system}"
            else:
                result.result = CheckResult.WARNING
                result.message = f"Optional classification missing: {system}"
            return result

        if value_pattern and not re.match(value_pattern, str(value)):
            result.result = CheckResult.FAIL
            result.message = f"Classification '{value}' does not match pattern"
            return result

        result.message = f"Classification {system} = {value}"
        return result

    def check_model(self, elements: List[Dict[str, Any]],
                    spec_id: str) -> Dict[str, Any]:
        """Check all elements against specification."""

        self.results = []

        for element in elements:
            element_results = self.check_element(element, spec_id)
            self.results.extend(element_results)

        # Summarize results
        pass_count = sum(1 for r in self.results if r.result == CheckResult.PASS)
        fail_count = sum(1 for r in self.results if r.result == CheckResult.FAIL)
        warning_count = sum(1 for r in self.results if r.result == CheckResult.WARNING)

        return {
            'specification': spec_id,
            'elements_checked': len(elements),
            'total_checks': len(self.results),
            'passed': pass_count,
            'failed': fail_count,
            'warnings': warning_count,
            'compliance_rate': round(pass_count / len(self.results) * 100, 1) if self.results else 0,
            'status': 'COMPLIANT' if fail_count == 0 else 'NON-COMPLIANT'
        }

    def get_failed_checks(self) -> List[Dict[str, Any]]:
        """Get list of failed checks."""

        return [
            {
                'element_id': r.element_id,
                'element_type': r.element_type,
                'requirement': r.requirement_id,
                'message': r.message,
                'details': r.details
            }
            for r in self.results if r.result == CheckResult.FAIL
        ]

    def export_to_excel(self, output_path: str) -> str:
        """Export validation results to Excel."""

        with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
            # Summary
            summary = {
                'Total Checks': len(self.results),
                'Passed': sum(1 for r in self.results if r.result == CheckResult.PASS),
                'Failed': sum(1 for r in self.results if r.result == CheckResult.FAIL),
                'Warnings': sum(1 for r in self.results if r.result == CheckResult.WARNING)
            }
            summary_df = pd.DataFrame([summary])
            summary_df.to_excel(writer, sheet_name='Summary', index=False)

            # All results
            results_df = pd.DataFrame([{
                'Element ID': r.element_id,
                'Element Type': r.element_type,
                'Requirement': r.requirement_id,
                'Result': r.result.value,
                'Message': r.message
            } for r in self.results])
            results_df.to_excel(writer, sheet_name='All Results', index=False)

            # Failed only
            failed_df = pd.DataFrame(self.get_failed_checks())
            if not failed_df.empty:
                failed_df.to_excel(writer, sheet_name='Failed', index=False)

        return output_path

Read the full file on GitHub · 511 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. 9d ago First seen · 511 lines · 21 tokens per session scan A 34234406b877

Subscribe to this mod's changes

ids-checker 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 21 tokens to every session and 3,791 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 2026-09-03.