Urban-Design-Skills-Claude

Urban-Design-Skills-Claude is a plugin for Claude Code from Abhinavbwj/Urban-Design-Skills-Claude. Its manifest loads nothing; the 18 skills it bundles cost 2,086 tokens per session together, scanned A, original, MIT.

A set of 18 Claude Code skills for planning and evaluating urban areas, including streets, public spaces, transport, zoning, sustainability, and redevelopment. Urban design is the planning of how buildings, streets, parks, and movement fit together in a place.

In plain words
What is it for?
Use it for site analysis, masterplans, street and public-space design, transit-oriented development, mobility studies, sustainability scoring, zoning, cost estimates, urban regeneration, and computational urban metrics.
Why use it?
It gives a coding agent domain-specific guidance when software work involves urban planning instead of requiring the user to explain each planning concept from scratch. It brings together named planning methods, standards, and calculation tools described in the add-on.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest. Also seen: mentions Claude Code.

Good fit Use it for site analysis, masterplans, street and public-space design, transit-oriented development, mobility studies, sustainability scoring, zoning, cost estimates, urban regeneration, and computational urban metrics.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add Abhinavbwj/Urban-Design-Skills-Claude/plugin install Urban-Design-Skills-Claude
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.

Clone the repo
git clone --depth 1 https://github.com/Abhinavbwj/Urban-Design-Skills-Claude

Made for: Claude Code.

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 Urban-Design-Skills-Claude

README.md
[![agentmods](https://agentmods.dev/badge/plugins/abhinavbwj/urban-design-skills-claude/urban-design-skills-claude/github.svg)](https://agentmods.dev/plugins/abhinavbwj/urban-design-skills-claude/urban-design-skills-claude)
Your own site
<a href="https://agentmods.dev/plugins/abhinavbwj/urban-design-skills-claude/urban-design-skills-claude"><img src="https://agentmods.dev/badge/plugins/abhinavbwj/urban-design-skills-claude/urban-design-skills-claude/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 Urban-Design-Skills-Claude

Your own site · 80×15
<a href="https://agentmods.dev/plugins/abhinavbwj/urban-design-skills-claude/urban-design-skills-claude"><img src="https://agentmods.dev/badge/plugins/abhinavbwj/urban-design-skills-claude/urban-design-skills-claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 18 skills cost 2,086 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

Urban-Design-Skills-Claude 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 12d 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.

.claude-plugin/plugin.json · 36 lines

What it actually says

{
  "name": "urban-design-skills",
  "version": "1.2.0",
  "description": "18 specialized Claude Code skills for urban design covering site analysis, masterplanning, street design, public space design, sustainability scoring, zoning, transit-oriented development, mobility and transport planning, cost estimation, urban regeneration, and computational urban metrics. References 40+ theorists and frameworks including Kevin Lynch, Jane Jacobs, Christopher Alexander, Jan Gehl, Andres Duany, and standards from NACTO, ITDP, ITE, CROW, ICOMOS, UN-Habitat, LEED-ND, BREEAM, and more. Includes 7 Python calculators.",
  "author": {
    "name": "Abhinav Bhardwaj",
    "copyright": "Copyright (c) 2026 Abhinav Bhardwaj. All rights reserved."
  },
  "license": "MIT",
  "keywords": [
    "urban-design",
    "architecture",
    "masterplanning",
    "sustainability",
    "LEED-ND",
    "NACTO",
    "transit-oriented-development",
    "street-design",
    "public-space",
    "zoning",
    "form-based-codes",
    "walkability",
    "density",
    "AEC",
    "mobility",
    "transport-planning",
    "trip-generation",
    "cost-estimation",
    "feasibility",
    "urban-regeneration",
    "brownfield",
    "adaptive-reuse",
    "heritage"
  ]
}
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. 12d ago First seen · 36 lines scan A 97ce04a8708b

Subscribe to this mod's changes

Urban-Design-Skills-Claude is a plugin published in the GitHub repository Abhinavbwj/Urban-Design-Skills-Claude (129 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories