agentmods.dev

bharatlas

bharatlas is a skill for Claude Code from urbanmorph/geodata. It costs 194 tokens per session (1,248 once invoked), scanned A, original, MIT.

A tool for querying India-only geographic and administrative data, such as states, districts, villages, wards, pincodes, environmental zones, infrastructure, and nearby features.

In plain words
What is it for?
Use it to identify Indian administrative areas, inspect hazards and infrastructure, search around coordinates, download map layers for geographic-information systems, or create and publish a field-data collection map.
Why use it?
It provides structured answers about what a place or coordinate belongs to and what geographic features are nearby, including data that may come from community submissions.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the bharatlas plugin — 1 skill shipped together

not rated 39repo 2d ago A scan SkillSpector: pass 194 tokens original MIT

Good fit Use it to identify Indian administrative areas, inspect hazards and infrastructure, search around coordinates, download map layers for geographic-information systems, or create and publish a field-data collection map.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/urbanmorph/geodata/bharatlas
View source ↗ urbanmorph/geodata
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 urbanmorph/geodata --skill bharatlas
Clone the repo
git clone --depth 1 https://github.com/urbanmorph/geodata

Made for: Claude Code.

Or install bharatlas, the plugin that ships this one along with the rest of its 1 skill.

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 bharatlas

README.md
[![agentmods](https://agentmods.dev/badge/skills/urbanmorph/geodata/bharatlas/github.svg)](https://agentmods.dev/skills/urbanmorph/geodata/bharatlas)
Your own site
<a href="https://agentmods.dev/skills/urbanmorph/geodata/bharatlas"><img src="https://agentmods.dev/badge/skills/urbanmorph/geodata/bharatlas/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 bharatlas

Your own site · 80×15
<a href="https://agentmods.dev/skills/urbanmorph/geodata/bharatlas"><img src="https://agentmods.dev/badge/skills/urbanmorph/geodata/bharatlas.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,248 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 $0.00194 $0.01248
Opus 5 $0.00097 $0.00624
Sonnet 5 $0.00039 $0.00250
Haiku 4.5 $0.00019 $0.00125

Measured 9d ago against content hash 583495f8ce89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

bharatlas 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.

plugins/claude-code/skills/bharatlas/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bharatlas: India's open geo atlas via MCP

bharatlas (bharatlas.com) is India's open geo data catalog. This skill drives 17 MCP tools: a read side over curated layers plus community submissions, and an authoring side for collect maps.

When to use

  • Any question about Indian administrative geography (state to village), city wards, constituencies, pincodes.
  • Environment / infrastructure / hazard data: forests, wildlife, rivers, reservoirs, dams, groundwater, agro zones, hospitals, highways, airports, flood and seismic zones.
  • "What is at this coordinate?" or "what is near this point?" in India.
  • Downloading a layer in a GIS format.
  • Running a field data collection with collect and publishing the result.

When NOT to use

  • Directions, traffic, or finding a business (that is Google Maps, not bharatlas).
  • Editing the base map itself (that is OpenStreetMap).
  • Geography outside India (bharatlas is India-only).

Read workflow

  1. Discover: list_layers (filter by category, level, source, or q search) and list_categories. Always check list_submissions too, community layers may cover topics the curated set does not.
  2. Schema first: call get_layer_schema BEFORE query_layer. Column names vary by source ("state" vs "State_LGD" vs "stname"); the schema shows exact names and sample values.
  3. Query: query_layer with where (case-insensitive column=value), select, or group_by for counts. Reads the parquet at runtime.
  4. Locate: locate with lat/lng returns every admin boundary and zone containing that point in one call. The "where am I?" tool.
  5. Nearby: nearby finds features of a layer within a radius (points, lines, or polygons).
  6. Download: get_layer_detail returns direct URLs for parquet, pmtiles, geojson, kml, shapefile.

Source preference

  • Admin boundaries (state to village): prefer LGD (lgd_*) as authoritative. SOI, Bhuvan, geoBoundaries are cross-reference alternates; mention them if the user asks about discrepancies.
  • City wards: one layer per city (wards_chennai, wards_pune, ...); some cities have multiple vintages.
  • Always join on LGD codes, not names (spellings drift across sources).

Read the full file on GitHub · 68 lines

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 · 68 lines · 194 tokens per session scan A 583495f8ce89

Subscribe to this mod's changes

bharatlas is a skill published in the GitHub repository urbanmorph/geodata (39 stars, last pushed 2d ago), licensed MIT. It adds 194 tokens to every session and 1,248 once invoked, about $0.0010 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 2026-08-30.

LLMMapsResearchgeospatialgisindiamcp
Related

Other skills, from other repositories

opengis-skills

Use when AI coding assistant needs GIS/CAD/C#/AI/IoT/3D domain expertise for 73+ open-source projects. One-stop skill index with tag-based search and on-demand loading for GDAL, GeoServer, QGIS, PostGIS, JTS, CesiumJS, FreeCAD, OpenSCAD, OCCT, NPOI, SqlSugar, Furion, Dify, SuperSplat, Go and more.

znlgis/opengis-skills · 97 tokens

gdal-api

Use when programming against GDAL/OGR in C, C++, Python, or .NET for raster/vector I/O, coordinate transformation, or custom geospatial algorithms. GDAL API: low-level programming interface for reading/writing 70+ geospatial formats.

znlgis/opengis-skills · 56 tokens

gdal

Use when processing geospatial raster/vector data via command line — format conversion (Shapefile to GeoJSON), reprojection, DEM analysis, NDVI calculation, mosaicking. GDAL/OGR CLI: the industry standard for batch geospatial data processing with 50+ command-line tools (ogr2ogr, gdalwarp, gdaltranslate, gdalcalc).

znlgis/opengis-skills · 77 tokens

maptiler

Expert coding skill for the full MapTiler platform — Cloud REST APIs, MapTiler SDK JS (built on MapLibre GL JS), native mobile SDKs, on-premise infrastructure, and vector tile schemas. USE WHEN the user wants to add a map to a web or mobile app, show locations or routes, display geographic data, build a store locator…

maptiler/maptiler-skills · 294 tokens

gis-skills

Use when processing geospatial data, publishing map services, querying spatial databases, performing geometry operations, or building web map applications. Index of 23 skills: GDAL, GeoServer, QGIS, PostGIS, JTS, GeoPandas, Shapely, CesiumJS, OpenLayers, NetTopologySuite and more.

znlgis/opengis-skills · 71 tokens

gemgis

Spatial data processing for geological modelling with GemPy. Use when Claude needs to: (1) Prepare spatial data for GemPy models, (2) Extract interface points from geological maps, (3) Process orientations/dip measurements, (4) Sample DEMs along profiles or cross-sections, (5) Convert between GIS formats and GemPy…

SteadfastAsArt/geoscience-skills · 102 tokens