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 gantt-chartgit 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/gantt-chart)<a href="https://agentmods.dev/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/gantt-chart"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/gantt-chart/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/gantt-chart"><img src="https://agentmods.dev/badge/skills/datadrivenconstruction/ddc_skills_for_ai_agents_in_construction/gantt-chart.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 79 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00022 | $0.02791 |
| Opus 5 | $0.00011 | $0.01396 |
| Sonnet 5 | $0.00004 | $0.00558 |
| Haiku 4.5 | $0.00002 | $0.00279 |
Grade A, and why
gantt-chart 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- gantt-chart — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gantt Chart Generator
Business Case
Problem Statement
Schedule visualization challenges:
- Complex task dependencies
- Progress tracking
- Critical path visibility
- Multi-level WBS display
Solution
Generate interactive Gantt charts from schedule data with dependency visualization, progress tracking, and export capabilities.
Technical Implementation
import pandas as pd
from typing import Dict, Any, List, Optional
from dataclasses import dataclass, field
from datetime import date, timedelta
from enum import Enum
class TaskStatus(Enum):
NOT_STARTED = "not_started"
IN_PROGRESS = "in_progress"
COMPLETED = "completed"
DELAYED = "delayed"
ON_HOLD = "on_hold"
class DependencyType(Enum):
FS = "finish_to_start"
SS = "start_to_start"
FF = "finish_to_finish"
SF = "start_to_finish"
@dataclass
class Task:
task_id: str
name: str
start_date: date
end_date: date
wbs_code: str = ""
progress: float = 0 # 0-100
status: TaskStatus = TaskStatus.NOT_STARTED
assignee: str = ""
level: int = 0
is_milestone: bool = False
is_summary: bool = False
parent_id: str = ""
@dataclass
class Dependency:
predecessor_id: str
successor_id: str
dep_type: DependencyType = DependencyType.FS
lag: int = 0
class GanttChartGenerator:
"""Generate Gantt charts for construction scheduling."""
def __init__(self, project_name: str):
self.project_name = project_name
self.tasks: Dict[str, Task] = {}
self.dependencies: List[Dependency] = []
def add_task(self, task: Task):
"""Add task to chart."""
self.tasks[task.task_id] = task
def add_dependency(self, predecessor_id: str, successor_id: str,
dep_type: DependencyType = DependencyType.FS,
lag: int = 0):
"""Add dependency between tasks."""
self.dependencies.append(Dependency(
predecessor_id=predecessor_id,
successor_id=successor_id,
dep_type=dep_type,
lag=lag
))
def import_from_df(self, df: pd.DataFrame):
"""Import tasks from DataFrame."""
for _, row in df.iterrows():
task = Task(
task_id=str(row['task_id']),
name=row['name'],
start_date=pd.to_datetime(row['start_date']).date(),
end_date=pd.to_datetime(row['end_date']).date(),
wbs_code=str(row.get('wbs_code', '')),
progress=float(row.get('progress', 0)),
level=int(row.get('level', 0)),
is_milestone=bool(row.get('is_milestone', False)),
is_summary=bool(row.get('is_summary', False)),
parent_id=str(row.get('parent_id', ''))
)
self.add_task(task)
def get_project_range(self) -> tuple:
"""Get project date range."""
if not self.tasks:
return (date.today(), date.today())
min_date = min(t.start_date for t in self.tasks.values())
max_date = max(t.end_date for t in self.tasks.values())
return (min_date, max_date)
def get_duration(self, task_id: str) -> int:
"""Get task duration in days."""
task = self.tasks.get(task_id)
if task:
return (task.end_date - task.start_date).days + 1
return 0
def generate_text_gantt(self, width: int = 60) -> str:
"""Generate text-based Gantt chart."""
if not self.tasks:
return "No tasks"
lines = []
start, end = self.get_project_range()
total_days = (end - start).days + 1
scale = width / total_days if total_days > 0 else 1
# Header
lines.append(f"Project: {self.project_name}")
lines.append(f"Period: {start} to {end}")
lines.append("-" * (40 + width))
# Tasks
for task in sorted(self.tasks.values(), key=lambda t: (t.level, t.start_date)):
indent = " " * task.level
name = f"{indent}{task.name}"[:35].ljust(35)
# Bar position
bar_start = int((task.start_date - start).days * scale)
bar_length = max(1, int(self.get_duration(task.task_id) * scale))
# Progress bar
progress_length = int(bar_length * task.progress / 100)
bar = " " * bar_start
bar += "█" * progress_length
bar += "░" * (bar_length - progress_length)
bar = bar[:width].ljust(width)
status_char = "◆" if task.is_milestone else "│"
lines.append(f"{name} {status_char}{bar}│ {task.progress:.0f}%")
return "\n".join(lines)
def generate_mermaid_gantt(self) -> str:
"""Generate Mermaid Gantt diagram."""
lines = [
"gantt",
f" title {self.project_name}",
" dateFormat YYYY-MM-DD",
""
]
# Group by WBS prefix
sections = {}
for task in self.tasks.values():
section = task.wbs_code.split('.')[0] if task.wbs_code else "Tasks"
if section not in sections:
sections[section] = []
sections[section].append(task)
for section, tasks in sections.items():
lines.append(f" section {section}")
for task in sorted(tasks, key=lambda t: t.start_date):
duration = self.get_duration(task.task_id)
status = ""
if task.status == TaskStatus.COMPLETED:
status = "done, "
elif task.status == TaskStatus.IN_PROGRESS:
status = "active, "
if task.is_milestone:
lines.append(f" {task.name} :milestone, {task.start_date}, 0d")
else:
lines.append(f" {task.name} :{status}{task.task_id}, {task.start_date}, {duration}d")
return "\n".join(lines)
def generate_html_gantt(self) -> str:
"""Generate HTML/CSS Gantt chart."""
start, end = self.get_project_range()
total_days = (end - start).days + 1
html = f"""
<!DOCTYPE html>
<html>
<head>
<title>Gantt Chart - {self.project_name}</title>
<style>
.gantt {{ font-family: Arial, sans-serif; }}
.task {{ display: flex; margin: 2px 0; height: 25px; align-items: center; }}
.task-name {{ width: 200px; padding-right: 10px; font-size: 12px; }}
.task-bar {{ position: relative; height: 20px; background: #e0e0e0; flex: 1; }}
.bar {{ position: absolute; height: 100%; }}
.bar-fill {{ background: #4CAF50; }}
.bar-progress {{ background: #2196F3; }}
.milestone {{ width: 10px; height: 10px; background: #FF5722; transform: rotate(45deg); margin-left: 10px; }}
</style>
</head>
<body>
<div class="gantt">
<h2>{self.project_name}</h2>
<p>{start} - {end}</p>
"""
for task in sorted(self.tasks.values(), key=lambda t: (t.level, t.start_date)):
left = ((task.start_date - start).days / total_days) * 100
width = (self.get_duration(task.task_id) / total_days) * 100
progress_width = width * task.progress / 100
indent = " " * (task.level * 4)
if task.is_milestone:
html += f'<div class="task"><div class="task-name">{indent}{task.name}</div><div class="task-bar"><div class="milestone" style="left:{left}%"></div></div></div>\n'
else:
html += f'''<div class="task">
<div class="task-name">{indent}{task.name}</div>
<div class="task-bar">
<div class="bar bar-fill" style="left:{left}%; width:{width}%"></div>
<div class="bar bar-progress" style="left:{left}%; width:{progress_width}%"></div>
</div>
</div>\n'''
html += "</div></body></html>"
return html
def get_critical_path(self) -> List[str]:
"""Identify critical path tasks (simplified)."""
if not self.dependencies:
return [t.task_id for t in sorted(self.tasks.values(), key=lambda x: x.end_date)[-5:]]
# Find tasks with no slack (simplified approach)
critical = []
_, project_end = self.get_project_range()
for task in self.tasks.values():
if task.end_date == project_end:
critical.append(task.task_id)
# Trace predecessors
for dep in self.dependencies:
if dep.successor_id == task.task_id:
critical.append(dep.predecessor_id)
return list(set(critical))
def export_to_excel(self, output_path: str) -> str:
"""Export Gantt data to Excel."""
with pd.ExcelWriter(output_path, engine='openpyxl') as writer:
# Tasks
tasks_df = pd.DataFrame([{
'ID': t.task_id,
'WBS': t.wbs_code,
'Name': t.name,
'Start': t.start_date,
'End': t.end_date,
'Duration': self.get_duration(t.task_id),
'Progress': t.progress,
'Status': t.status.value,
'Level': t.level
} for t in self.tasks.values()])
tasks_df.to_excel(writer, sheet_name='Tasks', index=False)
# Dependencies
deps_df = pd.DataFrame([{
'Predecessor': d.predecessor_id,
'Successor': d.successor_id,
'Type': d.dep_type.value,
'Lag': d.lag
} for d in self.dependencies])
deps_df.to_excel(writer, sheet_name='Dependencies', index=False)
return output_path
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.
- 9d ago First seen · 346 lines · 22 tokens per session scan A e8fb10f43366
gantt-chart 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 22 tokens to every session and 2,791 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.
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.
plan
Plan features spanning multiple domains: billing (Stripe), auth (RBAC), real-time (Presence), webhooks, jobs (Oban). Use when designing interconnected systems or converting review findings into tasks.
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.
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).
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
proposal-writer
Write a client proposal, quote, scope of work, or engagement letter for a service business. Covers project understanding, scope, timeline, pricing presentation, and terms. Use whenever the user asks for a proposal, quote, project proposal, client proposal, SOW, statement of work, engagement letter, or B2B service…