quality-control-workflow

quality-control-workflow is a skill for Claude Code, Codex from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction. It costs 30 tokens per session (3,411 once invoked), scanned A, original, MIT.

A construction quality-control workflow for planning inspections, recording defects, and verifying that work meets project specifications.

In plain words
What is it for?
Use it to schedule inspections, log measurements and photos, create non-conformance reports, assign fixes, and confirm resolution.
Why use it?
It gives teams a structured way to follow defects from discovery to correction and closure, reducing missed issues and rework.

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 schedule inspections, log measurements and photos, create non-conformance reports, assign fixes, and confirm resolution.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/quality-control-workflow
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 quality-control-workflow
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 quality-control-workflow

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/quality-control-workflow"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/quality-control-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,411 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 $0.00030 $0.03411
Opus 5 $0.00015 $0.01706
Sonnet 5 $0.00006 $0.00682
Haiku 4.5 $0.00003 $0.00341

Measured 9d ago against content hash 7824725b8beb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

quality-control-workflow 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:

3_DDC_Insights/Safety-Quality/quality-control-workflow/SKILL.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Quality Control Workflow

Overview

Automate construction quality control workflows from inspection planning through defect resolution. Track quality metrics, manage non-conformance reports (NCRs), and ensure specification compliance.

"Structured QC workflows reduce rework by 40% and improve first-time quality" — DDC Community

QC Workflow Stages

┌─────────────────────────────────────────────────────────────────┐
│                    QC WORKFLOW PIPELINE                          │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  Plan        →    Inspect    →    Document    →    Resolve      │
│  ────             ───────         ────────         ───────      │
│  📋 ITP           🔍 Check        📝 NCR           🔧 Fix        │
│  📅 Schedule      📸 Photo        📊 Log           ✅ Verify     │
│  👥 Assign        📏 Measure      📧 Notify        📈 Close      │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Technical Implementation

from dataclasses import dataclass, field
from typing import List, Dict, Optional
from enum import Enum
from datetime import datetime, timedelta
import json

class QCStatus(Enum):
    PENDING = "pending"
    IN_PROGRESS = "in_progress"
    PASSED = "passed"
    FAILED = "failed"
    ON_HOLD = "on_hold"

class DefectSeverity(Enum):
    CRITICAL = "critical"  # Stop work, structural/safety issue
    MAJOR = "major"        # Must fix before cover-up
    MINOR = "minor"        # Fix before completion
    COSMETIC = "cosmetic"  # Punch list item

class NCRStatus(Enum):
    DRAFT = "draft"
    ISSUED = "issued"
    ACCEPTED = "accepted"
    DISPUTED = "disputed"
    IN_REMEDIATION = "in_remediation"
    VERIFIED = "verified"
    CLOSED = "closed"

@dataclass
class InspectionPoint:
    id: str
    name: str
    spec_reference: str
    acceptance_criteria: str
    inspection_method: str
    hold_point: bool = False  # Requires sign-off before proceeding
    witness_point: bool = False  # Client/engineer may witness

@dataclass
class QCInspection:
    id: str
    inspection_point: InspectionPoint
    location: str
    scheduled_date: datetime
    inspector: str
    status: QCStatus = QCStatus.PENDING
    actual_date: Optional[datetime] = None
    result: str = ""
    measurements: Dict[str, float] = field(default_factory=dict)
    photos: List[str] = field(default_factory=list)
    notes: str = ""
    sign_off_by: str = ""

@dataclass
class Defect:
    id: str
    inspection_id: str
    description: str
    location: str
    severity: DefectSeverity
    spec_reference: str
    photos: List[str] = field(default_factory=list)
    assigned_to: str = ""
    due_date: Optional[datetime] = None
    status: str = "open"
    root_cause: str = ""
    corrective_action: str = ""
    verified_by: str = ""
    closed_date: Optional[datetime] = None

@dataclass
class NonConformanceReport:
    id: str
    defect_ids: List[str]
    title: str
    description: str
    contractor: str
    spec_sections: List[str]
    status: NCRStatus = NCRStatus.DRAFT
    issued_date: Optional[datetime] = None
    response_due: Optional[datetime] = None
    contractor_response: str = ""
    remediation_plan: str = ""
    cost_impact: float = 0.0
    schedule_impact_days: int = 0

class QualityControlManager:
    """Manage construction quality control workflow."""

    def __init__(self, project_id: str, project_name: str):
        self.project_id = project_id
        self.project_name = project_name
        self.inspection_points: Dict[str, InspectionPoint] = {}
        self.inspections: Dict[str, QCInspection] = {}
        self.defects: Dict[str, Defect] = {}
        self.ncrs: Dict[str, NonConformanceReport] = {}

    def create_itp(self, work_package: str, inspection_points: List[Dict]) -> List[InspectionPoint]:
        """Create Inspection and Test Plan (ITP)."""
        created = []
        for idx, point in enumerate(inspection_points):
            ip = InspectionPoint(
                id=f"{work_package}-{idx+1:03d}",
                name=point['name'],
                spec_reference=point.get('spec_ref', ''),
                acceptance_criteria=point.get('criteria', ''),
                inspection_method=point.get('method', 'Visual'),
                hold_point=point.get('hold_point', False),
                witness_point=point.get('witness_point', False)
            )
            self.inspection_points[ip.id] = ip
            created.append(ip)
        return created

    def schedule_inspection(self, inspection_point_id: str, location: str,
                           scheduled_date: datetime, inspector: str) -> QCInspection:
        """Schedule a QC inspection."""
        if inspection_point_id not in self.inspection_points:
            raise ValueError(f"Inspection point {inspection_point_id} not found")

        inspection_id = f"QCI-{datetime.now().strftime('%Y%m%d%H%M%S')}"
        inspection = QCInspection(
            id=inspection_id,
            inspection_point=self.inspection_points[inspection_point_id],
            location=location,
            scheduled_date=scheduled_date,
            inspector=inspector
        )
        self.inspections[inspection_id] = inspection
        return inspection

    def conduct_inspection(self, inspection_id: str, result: str,
                          measurements: Dict[str, float] = None,
                          photos: List[str] = None,
                          notes: str = "") -> QCInspection:
        """Record inspection results."""
        if inspection_id not in self.inspections:
            raise ValueError(f"Inspection {inspection_id} not found")

        inspection = self.inspections[inspection_id]
        inspection.actual_date = datetime.now()
        inspection.result = result
        inspection.measurements = measurements or {}
        inspection.photos = photos or []
        inspection.notes = notes
        inspection.status = QCStatus.PASSED if result == "pass" else QCStatus.FAILED

        return inspection

    def record_defect(self, inspection_id: str, description: str,
                     location: str, severity: DefectSeverity,
                     spec_reference: str, photos: List[str] = None,
                     assigned_to: str = "") -> Defect:
        """Record a defect from inspection."""
        defect_id = f"DEF-{datetime.now().strftime('%Y%m%d%H%M%S')}"

        # Set due date based on severity
        due_days = {
            DefectSeverity.CRITICAL: 1,
            DefectSeverity.MAJOR: 3,
            DefectSeverity.MINOR: 7,
            DefectSeverity.COSMETIC: 14
        }

        defect = Defect(
            id=defect_id,
            inspection_id=inspection_id,
            description=description,
            location=location,
            severity=severity,
            spec_reference=spec_reference,
            photos=photos or [],
            assigned_to=assigned_to,
            due_date=datetime.now() + timedelta(days=due_days[severity])
        )

        self.defects[defect_id] = defect
        return defect

    def create_ncr(self, defect_ids: List[str], title: str,
                  contractor: str, description: str = "") -> NonConformanceReport:
        """Create Non-Conformance Report from defects."""
        ncr_id = f"NCR-{datetime.now().strftime('%Y%m%d%H%M%S')}"

        # Collect spec references from defects
        spec_sections = []
        for def_id in defect_ids:
            if def_id in self.defects:
                spec_sections.append(self.defects[def_id].spec_reference)

        ncr = NonConformanceReport(
            id=ncr_id,
            defect_ids=defect_ids,
            title=title,
            description=description or self._generate_ncr_description(defect_ids),
            contractor=contractor,
            spec_sections=list(set(spec_sections)),
            response_due=datetime.now() + timedelta(days=5)
        )

        self.ncrs[ncr_id] = ncr
        return ncr

    def _generate_ncr_description(self, defect_ids: List[str]) -> str:
        """Generate NCR description from defects."""
        lines = ["The following non-conformances have been identified:", ""]
        for def_id in defect_ids:
            if def_id in self.defects:
                d = self.defects[def_id]
                lines.append(f"- {d.description} at {d.location}")
                lines.append(f"  Reference: {d.spec_reference}")
        return "\n".join(lines)

    def issue_ncr(self, ncr_id: str) -> NonConformanceReport:
        """Issue NCR to contractor."""
        if ncr_id not in self.ncrs:
            raise ValueError(f"NCR {ncr_id} not found")

        ncr = self.ncrs[ncr_id]
        ncr.status = NCRStatus.ISSUED
        ncr.issued_date = datetime.now()
        return ncr

    def record_ncr_response(self, ncr_id: str, response: str,
                           remediation_plan: str, cost_impact: float = 0,
                           schedule_impact: int = 0) -> NonConformanceReport:
        """Record contractor response to NCR."""
        if ncr_id not in self.ncrs:
            raise ValueError(f"NCR {ncr_id} not found")

        ncr = self.ncrs[ncr_id]
        ncr.contractor_response = response
        ncr.remediation_plan = remediation_plan
        ncr.cost_impact = cost_impact
        ncr.schedule_impact_days = schedule_impact
        ncr.status = NCRStatus.ACCEPTED
        return ncr

    def verify_remediation(self, ncr_id: str, verified_by: str) -> NonConformanceReport:
        """Verify NCR remediation is complete."""
        if ncr_id not in self.ncrs:
            raise ValueError(f"NCR {ncr_id} not found")

        ncr = self.ncrs[ncr_id]
        ncr.status = NCRStatus.VERIFIED

        # Close associated defects
        for def_id in ncr.defect_ids:
            if def_id in self.defects:
                self.defects[def_id].status = "closed"
                self.defects[def_id].verified_by = verified_by
                self.defects[def_id].closed_date = datetime.now()

        return ncr

    def get_quality_metrics(self) -> Dict:
        """Calculate quality metrics."""
        total_inspections = len(self.inspections)
        passed = len([i for i in self.inspections.values() if i.status == QCStatus.PASSED])
        failed = len([i for i in self.inspections.values() if i.status == QCStatus.FAILED])

        open_defects = len([d for d in self.defects.values() if d.status == "open"])
        overdue_defects = len([d for d in self.defects.values()
                              if d.status == "open" and d.due_date and d.due_date < datetime.now()])

        open_ncrs = len([n for n in self.ncrs.values()
                        if n.status not in [NCRStatus.VERIFIED, NCRStatus.CLOSED]])

        return {
            "total_inspections": total_inspections,
            "passed_inspections": passed,
            "failed_inspections": failed,
            "first_time_pass_rate": (passed / total_inspections * 100) if total_inspections else 0,
            "open_defects": open_defects,
            "overdue_defects": overdue_defects,
            "open_ncrs": open_ncrs,
            "total_cost_impact": sum(n.cost_impact for n in self.ncrs.values()),
            "total_schedule_impact": sum(n.schedule_impact_days for n in self.ncrs.values())
        }

    def generate_qc_report(self) -> str:
        """Generate QC status report."""
        metrics = self.get_quality_metrics()

        lines = [
            f"# Quality Control Report",
            f"",
            f"**Project:** {self.project_name}",
            f"**Date:** {datetime.now().strftime('%Y-%m-%d')}",
            f"",
            f"## Summary Metrics",
            f"",
            f"| Metric | Value |",
            f"|--------|-------|",
            f"| First-Time Pass Rate | {metrics['first_time_pass_rate']:.1f}% |",
            f"| Open Defects | {metrics['open_defects']} |",
            f"| Overdue Defects | {metrics['overdue_defects']} |",
            f"| Open NCRs | {metrics['open_ncrs']} |",
            f"| Cost Impact | ${metrics['total_cost_impact']:,.0f} |",
            f"| Schedule Impact | {metrics['total_schedule_impact']} days |",
            f"",
        ]

        # Critical defects
        critical = [d for d in self.defects.values()
                   if d.severity == DefectSeverity.CRITICAL and d.status == "open"]
        if critical:
            lines.append("## Critical Open Defects")
            for d in critical:
                lines.append(f"- **{d.id}**: {d.description}")
                lines.append(f"  - Location: {d.location}")
                lines.append(f"  - Due: {d.due_date.strftime('%Y-%m-%d') if d.due_date else 'N/A'}")

        return "\n".join(lines)

Read the full file on GitHub · 397 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 · 397 lines · 30 tokens per session scan A 7824725b8beb

Subscribe to this mod's changes

quality-control-workflow 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 30 tokens to every session and 3,411 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.

Related

Other skills, from other repositories

catchup

Summarize and review what changed while you were away. Use after a weekend, vacation, or flight to check missed PRs, git commits, Linear tickets, and meetings — one prioritized brief, not a firehose.

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

lab:autoresearch

Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.

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

phx-deps-update

Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo). Use to upgrade/bump Elixir dependencies or when versions fall behind. NOT for deps.get failures (phx-investigate).

oliver-kriska/claude-elixir-phoenix · 62 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