look-ahead-scheduler

look-ahead-scheduler is a skill for Claude Code, Codex from datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction. It costs 38 tokens per session (3,544 once invoked), scanned A, original, MIT.

A short-term construction planning workflow that turns a long master schedule into rolling two-, three-, or six-week work plans.

In plain words
What is it for?
Use it to create look-ahead schedules, analyze constraints, assign crews, and coordinate daily work.
Why use it?
It exposes missing prerequisites and coordination problems early, giving crews time to remove constraints before work is due.

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 create look-ahead schedules, analyze constraints, assign crews, and coordinate daily work.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/look-ahead-scheduler
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 look-ahead-scheduler
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 look-ahead-scheduler

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/look-ahead-scheduler"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/look-ahead-scheduler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,544 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 $0.00038 $0.03544
Opus 5.5 $0.00015 $0.01418
Sonnet 5.5 $0.00008 $0.00709
Haiku 4.5 $0.00004 $0.00354

Measured 1mo ago against content hash e549fe94ea72, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

look-ahead-scheduler 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 1mo 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/Schedule-Optimization/look-ahead-scheduler/SKILL.md · 477 lines

How it starts

The opening of the file, as written. The whole thing — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Look-Ahead Scheduler

Overview

Generate rolling look-ahead schedules from the master schedule. Create actionable short-term plans with constraint analysis, crew assignments, and daily coordination.

"Look-ahead planning catches 80% of schedule problems before they occur" — DDC Community

Look-Ahead Hierarchy

┌─────────────────────────────────────────────────────────────────┐
│                    LOOK-AHEAD PLANNING                           │
├─────────────────────────────────────────────────────────────────┤
│                                                                  │
│  Master Schedule (12+ months)                                    │
│       ↓                                                         │
│  Phase Schedule (3-6 months)                                    │
│       ↓                                                         │
│  6-Week Look-Ahead (make-ready)                                 │
│       ↓                                                         │
│  3-Week Look-Ahead (constraint removal)                         │
│       ↓                                                         │
│  Weekly Work Plan (commitment)                                  │
│       ↓                                                         │
│  Daily Coordination                                              │
│                                                                  │
└─────────────────────────────────────────────────────────────────┘

Technical Implementation

from dataclasses import dataclass, field
from typing import List, Dict, Optional, Set
from datetime import datetime, timedelta
from enum import Enum
from collections import defaultdict

class ConstraintType(Enum):
    PREDECESSOR = "predecessor"
    LABOR = "labor"
    MATERIAL = "material"
    EQUIPMENT = "equipment"
    INFORMATION = "information"
    PERMIT = "permit"
    INSPECTION = "inspection"
    SPACE = "space"
    WEATHER = "weather"

class ConstraintStatus(Enum):
    OPEN = "open"
    IN_PROGRESS = "in_progress"
    RESOLVED = "resolved"
    BLOCKED = "blocked"

class ActivityStatus(Enum):
    NOT_STARTED = "not_started"
    IN_PROGRESS = "in_progress"
    COMPLETE = "complete"
    DELAYED = "delayed"

@dataclass
class Constraint:
    id: str
    activity_id: str
    constraint_type: ConstraintType
    description: str
    responsible_party: str
    needed_by: datetime
    status: ConstraintStatus = ConstraintStatus.OPEN
    resolution_notes: str = ""
    resolved_date: Optional[datetime] = None

@dataclass
class LookAheadActivity:
    id: str
    name: str
    trade: str
    location: str
    planned_start: datetime
    planned_finish: datetime
    duration: int
    labor_hours: float
    crew_size: int
    predecessors: List[str] = field(default_factory=list)
    constraints: List[Constraint] = field(default_factory=list)
    status: ActivityStatus = ActivityStatus.NOT_STARTED
    percent_complete: float = 0.0
    notes: str = ""
    can_start: bool = False

@dataclass
class WeeklyWorkPlan:
    week_start: datetime
    week_end: datetime
    activities: List[LookAheadActivity]
    total_labor_hours: float
    trades_involved: List[str]
    constraints_to_resolve: List[Constraint]

@dataclass
class DailyPlan:
    date: datetime
    activities: List[LookAheadActivity]
    labor_by_trade: Dict[str, int]
    equipment_needed: List[str]
    inspections: List[str]
    safety_focus: str

class LookAheadScheduler:
    """Generate rolling look-ahead schedules."""

    def __init__(self, project_name: str):
        self.project_name = project_name
        self.activities: Dict[str, LookAheadActivity] = {}
        self.constraints: Dict[str, Constraint] = {}
        self.weekly_plans: List[WeeklyWorkPlan] = []

    def import_from_master(self, master_activities: List[Dict],
                          look_ahead_start: datetime,
                          look_ahead_weeks: int = 6) -> int:
        """Import activities from master schedule for look-ahead period."""
        look_ahead_end = look_ahead_start + timedelta(weeks=look_ahead_weeks)
        count = 0

        for act in master_activities:
            start = datetime.fromisoformat(act['planned_start']) if isinstance(act['planned_start'], str) else act['planned_start']
            finish = datetime.fromisoformat(act['planned_finish']) if isinstance(act['planned_finish'], str) else act['planned_finish']

            # Include if overlaps look-ahead period
            if start <= look_ahead_end and finish >= look_ahead_start:
                activity = LookAheadActivity(
                    id=act['id'],
                    name=act['name'],
                    trade=act.get('trade', ''),
                    location=act.get('location', ''),
                    planned_start=start,
                    planned_finish=finish,
                    duration=act.get('duration', (finish - start).days),
                    labor_hours=act.get('labor_hours', 0),
                    crew_size=act.get('crew_size', 0),
                    predecessors=act.get('predecessors', [])
                )
                self.activities[activity.id] = activity
                count += 1

        return count

    def add_constraint(self, activity_id: str, constraint_type: ConstraintType,
                      description: str, responsible_party: str,
                      needed_by: datetime) -> Constraint:
        """Add constraint to activity."""
        constraint_id = f"CON-{len(self.constraints)+1:04d}"

        constraint = Constraint(
            id=constraint_id,
            activity_id=activity_id,
            constraint_type=constraint_type,
            description=description,
            responsible_party=responsible_party,
            needed_by=needed_by
        )

        self.constraints[constraint_id] = constraint

        if activity_id in self.activities:
            self.activities[activity_id].constraints.append(constraint)

        return constraint

    def update_constraint(self, constraint_id: str, status: ConstraintStatus,
                         notes: str = "") -> Constraint:
        """Update constraint status."""
        if constraint_id not in self.constraints:
            raise ValueError(f"Constraint {constraint_id} not found")

        constraint = self.constraints[constraint_id]
        constraint.status = status
        constraint.resolution_notes = notes

        if status == ConstraintStatus.RESOLVED:
            constraint.resolved_date = datetime.now()

        return constraint

    def analyze_make_ready(self) -> Dict[str, List[str]]:
        """Analyze which activities are 'make-ready' (constraints resolved)."""
        ready = []
        not_ready = []
        blocked = []

        for act in self.activities.values():
            # Check predecessors complete
            pred_complete = all(
                self.activities.get(p, {}).status == ActivityStatus.COMPLETE
                for p in act.predecessors if p in self.activities
            )

            # Check constraints resolved
            open_constraints = [c for c in act.constraints
                              if c.status != ConstraintStatus.RESOLVED]

            if not pred_complete:
                blocked.append(act.id)
                act.can_start = False
            elif open_constraints:
                not_ready.append(act.id)
                act.can_start = False
            else:
                ready.append(act.id)
                act.can_start = True

        return {
            "ready": ready,
            "not_ready": not_ready,
            "blocked": blocked
        }

    def generate_weekly_plan(self, week_start: datetime) -> WeeklyWorkPlan:
        """Generate weekly work plan."""
        week_end = week_start + timedelta(days=6)

        # Get activities for this week
        week_activities = [
            act for act in self.activities.values()
            if act.planned_start <= week_end and act.planned_finish >= week_start
        ]

        # Calculate totals
        total_hours = sum(act.labor_hours for act in week_activities)
        trades = list(set(act.trade for act in week_activities if act.trade))

        # Get constraints needing resolution this week
        constraints_due = [
            c for c in self.constraints.values()
            if c.status == ConstraintStatus.OPEN and c.needed_by <= week_end
        ]

        plan = WeeklyWorkPlan(
            week_start=week_start,
            week_end=week_end,
            activities=week_activities,
            total_labor_hours=total_hours,
            trades_involved=trades,
            constraints_to_resolve=constraints_due
        )

        self.weekly_plans.append(plan)
        return plan

    def generate_daily_plan(self, date: datetime) -> DailyPlan:
        """Generate daily coordination plan."""
        # Get activities for this day
        day_activities = [
            act for act in self.activities.values()
            if act.planned_start <= date <= act.planned_finish
            and act.can_start
        ]

        # Labor by trade
        labor_by_trade = defaultdict(int)
        for act in day_activities:
            labor_by_trade[act.trade] += act.crew_size

        # Equipment needed
        equipment = []
        for act in day_activities:
            for c in act.constraints:
                if c.constraint_type == ConstraintType.EQUIPMENT:
                    equipment.append(c.description)

        # Inspections
        inspections = [
            c.description for c in self.constraints.values()
            if c.constraint_type == ConstraintType.INSPECTION
            and c.needed_by.date() == date.date()
        ]

        # Safety focus based on activities
        safety_focus = self._determine_safety_focus(day_activities)

        return DailyPlan(
            date=date,
            activities=day_activities,
            labor_by_trade=dict(labor_by_trade),
            equipment_needed=equipment,
            inspections=inspections,
            safety_focus=safety_focus
        )

    def _determine_safety_focus(self, activities: List[LookAheadActivity]) -> str:
        """Determine daily safety focus based on activities."""
        # Keywords to safety topics
        keywords = {
            "excavation": "Excavation Safety - Shoring, sloping, access",
            "steel": "Steel Erection - Fall protection, crane safety",
            "concrete": "Concrete Pour - Silica, formwork, PPE",
            "roof": "Fall Protection - 100% tie-off, guardrails",
            "electrical": "Electrical Safety - LOTO, qualified personnel",
            "crane": "Crane Safety - Rigging, load charts, signaling",
            "welding": "Hot Work - Fire watch, permits, ventilation"
        }

        for act in activities:
            name_lower = act.name.lower()
            for keyword, safety in keywords.items():
                if keyword in name_lower:
                    return safety

        return "General Site Safety - PPE, housekeeping, awareness"

    def generate_look_ahead_report(self, weeks: int = 3) -> str:
        """Generate look-ahead schedule report."""
        self.analyze_make_ready()
        today = datetime.now()

        lines = [
            f"# {weeks}-Week Look-Ahead Schedule",
            f"",
            f"**Project:** {self.project_name}",
            f"**Generated:** {today.strftime('%Y-%m-%d')}",
            f"**Period:** {today.strftime('%Y-%m-%d')} to {(today + timedelta(weeks=weeks)).strftime('%Y-%m-%d')}",
            f"",
        ]

        # Summary
        make_ready = self.analyze_make_ready()
        lines.extend([
            f"## Summary",
            f"",
            f"- **Total Activities:** {len(self.activities)}",
            f"- **Ready to Start:** {len(make_ready['ready'])}",
            f"- **Awaiting Constraints:** {len(make_ready['not_ready'])}",
            f"- **Blocked:** {len(make_ready['blocked'])}",
            f""
        ])

        # Open constraints
        open_constraints = [c for c in self.constraints.values()
                          if c.status == ConstraintStatus.OPEN]
        if open_constraints:
            lines.extend([
                f"## Open Constraints ({len(open_constraints)})",
                f"",
                f"| Activity | Type | Description | Responsible | Needed By |",
                f"|----------|------|-------------|-------------|-----------|"
            ])
            for c in sorted(open_constraints, key=lambda x: x.needed_by):
                lines.append(
                    f"| {c.activity_id} | {c.constraint_type.value} | {c.description} | "
                    f"{c.responsible_party} | {c.needed_by.strftime('%Y-%m-%d')} |"
                )
            lines.append("")

        # Weekly breakdown
        for week_num in range(weeks):
            week_start = today + timedelta(weeks=week_num)
            week_start = week_start - timedelta(days=week_start.weekday())  # Monday

            plan = self.generate_weekly_plan(week_start)

            lines.extend([
                f"## Week {week_num + 1}: {plan.week_start.strftime('%b %d')} - {plan.week_end.strftime('%b %d')}",
                f"",
                f"**Activities:** {len(plan.activities)} | **Labor:** {plan.total_labor_hours:.0f} hrs | **Trades:** {', '.join(plan.trades_involved)}",
                f""
            ])

            if plan.activities:
                lines.append("| Activity | Trade | Location | Start | Duration | Status |")
                lines.append("|----------|-------|----------|-------|----------|--------|")
                for act in sorted(plan.activities, key=lambda a: a.planned_start):
                    status = "Ready" if act.can_start else "Constraint"
                    lines.append(
                        f"| {act.name} | {act.trade} | {act.location} | "
                        f"{act.planned_start.strftime('%m/%d')} | {act.duration}d | {status} |"
                    )
                lines.append("")

        return "\n".join(lines)

    def get_constraint_log(self) -> str:
        """Generate constraint log."""
        lines = [
            "# Constraint Log",
            "",
            "| ID | Activity | Type | Description | Responsible | Status | Needed By |",
            "|----|----------|------|-------------|-------------|--------|-----------|"
        ]

        for c in sorted(self.constraints.values(), key=lambda x: x.needed_by):
            lines.append(
                f"| {c.id} | {c.activity_id} | {c.constraint_type.value} | "
                f"{c.description} | {c.responsible_party} | {c.status.value} | "
                f"{c.needed_by.strftime('%Y-%m-%d')} |"
            )

        return "\n".join(lines)

Read the full file on GitHub · 477 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. 1mo ago First seen · 477 lines · 38 tokens per session scan A e549fe94ea72

Subscribe to this mod's changes

look-ahead-scheduler is a skill published in the GitHub repository datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction (374 stars, last pushed 8d ago), licensed MIT. It adds 38 tokens to every session and 3,544 once invoked, about $0.0002 per session on Opus 5.5. 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

process-mapper

Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…

alirezarezvani/claude-skills · 176 tokens

design-handoff-brief

Transform feature briefs into structured design briefs that give designers the context they need before opening Figma. Use when asked to write a design brief, create a design handoff, brief a designer on a new feature, or translate a PRD into design requirements. Produces a brief with user goal, emotional context…

mohitagw15856/pm-claude-skills · 83 tokens

estimating-and-contingency

Produces a cost or effort estimate someone can defend — decomposing the work, choosing between analogous, parametric and bottom-up methods, documenting the basis and its assumptions, expressing confidence as a range, and sizing contingency and management reserve separately. Use this to build an estimate, challenge one…

cbrock84/headcount · 87 tokens

scenario-team-admin

Use when administering a Scenario team from an agent through MCP: restricting which models a team or project can run (model access control, allowlist, blocklist), inviting or removing team and project members, changing roles, capping a member's Creative Unit spend, creating or deleting projects, auditing API keys and…

scenario-labs/skills · 101 tokens

rice-impact-matrix

Califica iniciativas usando tanto RICE como alineación estratégica para una priorización matizada. Úsalo cuando te pidan priorizar características, construir una matriz de prioridades, combinar puntuación cuantitativa con ajuste estratégico, o decidir qué construir después con múltiples iniciativas en competencia.…

mohitagw15856/pm-claude-skills · 93 tokens

multi-agent-client-onboarding

Uses Agent SDK to deploy 3 parallel agents for client onboarding -- workflow auditor, tech stack mapper, and strategy drafter. Real consulting workflow that produces a complete client assessment.

OneWave-AI/claude-skills · 41 tokens