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 pranava0x0/Commonwealth-MCP --skill site-context-screengit clone --depth 1 https://github.com/pranava0x0/Commonwealth-MCPWrote 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/pranava0x0/commonwealth-mcp/site-context-screen)<a href="https://agentmods.dev/skills/pranava0x0/commonwealth-mcp/site-context-screen"><img src="https://agentmods.dev/badge/skills/pranava0x0/commonwealth-mcp/site-context-screen/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/pranava0x0/commonwealth-mcp/site-context-screen"><img src="https://agentmods.dev/badge/skills/pranava0x0/commonwealth-mcp/site-context-screen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00085 | $0.01464 |
| Opus 5 | $0.00043 | $0.00732 |
| Sonnet 5 | $0.00017 | $0.00293 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
site-context-screen 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Site context screen
A first look at one location from the layers Virginia publishes statewide. Every answer here is what one published layer holds, and the gap between that and what is on the ground is the whole subject of this walk.
1. Establish the frame
Resolve the government first, and get to a point.
Most of these layers are queried by coordinate rather than by parcel, so the walk needs a point. When the caller gives an address, geocode it. When they give a parcel ID, look the parcel up first: the parcel polygon is what defines "on this ground", and the building step uses it rather than a radius when it is available.
A radius covers a circle of ground, which a property is not. When the walk falls back to one, say so in the answer: a caller who asked about a single lot and gets everything within 250 m has been answered a different question.
2. Minimum data walk
Ask for what the question needs, in this order, and stop when it is answered. Running all four every time is the anti-pattern this walk is built to avoid.
Step 1 — parcel.lookup, when there is a parcel ID. Gives the polygon
the rest of the walk can use. Skip it when the caller gave a point and did
not ask about a parcel.
Step 2 — building.lookup. Whether the ground is built on, and how
much of it.
- A hit gives footprints. Height, storey, and class fields are often null, which means the publisher holds no value rather than zero.
- Area is published in Web Mercator, where area is inflated by roughly 1.6x at Virginia's latitudes. Both the publisher's figure and a converted approximation come back, each labelled. Use the labelled one and say which.
- Empty is not vacant land. Coverage of this derived layer varies by locality, and a missing footprint is most often a coverage gap.
- A dense query truncates, returning the inline records and a handle to the whole retrieved set. Report the count, and use the handle rather than treating the short list as the answer.
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.
- yesterday Changed · +3 lines 64e14801342f
- 3d ago Changed 8bad5bb8126c
- 7d ago First seen · 129 lines · 85 tokens per session scan A 1e6edacf0f0b
site-context-screen is a skill published in the GitHub repository pranava0x0/Commonwealth-MCP (0 stars, last pushed today), licensed Apache-2.0. It adds 85 tokens to every session and 1,464 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
arcgis-portal-mcp
MCP server for ArcGIS Portal and ArcGIS Online. 70 tools for search, inspect, publish, query, manage, audit, and administer ArcGIS content. Use when: the user wants to work with feature services, web maps, layers, groups, users, webhooks, or portal administration through an AI assistant.
forthepeople-district-expansion
Skill for expanding ForThePeople.in to new districts. Use when adding Bengaluru Urban, Mysuru, or any new Indian district to the platform. Triggers: 'add district', 'expand to Bangalore', 'expand to Mysore', 'unlock district', 'new city', 'seed data for district', 'add Bengaluru', 'add Mysuru', 'district-specific…
ai-news-intelligence
AI News Intelligence pipeline for ForThePeople.in. Use this skill when building, debugging, or extending the automated news analysis system that reads Indian news, extracts civic data, and updates the district dashboard. Triggers: 'AI intelligence', 'news pipeline', 'Gemini analyzer', 'auto-update from news'…
indonesia-civic-stack
Query Indonesian government data portals via Python SDK, MCP tools, or REST API. 11 modules covering BPOM (food/drug), BPJPH (halal), AHU (companies), OJK (finance), OSS (business ID), LPSE (procurement), KPU (elections), LHKPN (wealth declarations), BPS (statistics), BMKG (weather/earthquakes), SIMBG (building…
indian-district-hierarchy
Complete Indian district administrative hierarchy for ForThePeople.in. Use this skill when building leadership pages, org charts, hierarchy visualizations, or seeding officer data for any Indian district. Triggers: 'district hierarchy', 'leadership org chart', 'who governs', 'district officers', 'tahsildar', 'block…
forthepeople-blueprint
Complete blueprint for building ForThePeople.in — India's citizen transparency platform. Use this skill whenever building ANY component, page, dashboard, scraper, API, database model, or UI element for ForThePeople.in. This includes: district dashboards, budget trackers, crop price modules, interactive maps…