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 federal-site-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/federal-site-screen)<a href="https://agentmods.dev/skills/pranava0x0/commonwealth-mcp/federal-site-screen"><img src="https://agentmods.dev/badge/skills/pranava0x0/commonwealth-mcp/federal-site-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/federal-site-screen"><img src="https://agentmods.dev/badge/skills/pranava0x0/commonwealth-mcp/federal-site-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 | $0.00106 | $0.01758 |
| Opus 5 | $0.00053 | $0.00879 |
| Sonnet 5 | $0.00021 | $0.00352 |
| Haiku 4.5 | $0.00011 | $0.00176 |
Grade A, and why
federal-site-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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Federal site screen
[[site-context-screen]] answers what is on and around a piece of ground from Virginia's own layers, and its only environmental layer is the state's water-quality monitoring stations. The constraints that stop a project are mostly federal: the flood map, the wetland inventory, the cleanup-site registers. Those are published, and a partner MCP server already exposes them.
This walk is the join. Its whole difficulty is that the two halves come from different servers with different provenance rules, and an answer that blends them into one paragraph destroys the reader's ability to check either. So it keeps two sets of claims over one point on the ground, and says which server produced each.
1. Establish the frame
- One point, carried forward unchanged. Everything downstream keys off a coordinate. Geocode once, resolve the government once, and pass the same coordinate to every subsequent step, including the partner's. Two halves screened at two slightly different points is the failure mode that produces a confident, internally inconsistent answer.
- The parcel is the unit a person cares about; the point is the unit the screens accept. Report both, and say when a parcel is large enough that a single-point screen says little about the rest of it.
- A screen tells you where to look next. Flood zone, wetland presence and cleanup-site proximity come from layers whose publishers name a different authority as the one that determines each. The reader is one step from treating the answer as a finding, and the answer has to keep saying who decides.
- The partner is not this registry. Its coverage, its dates and its limits are its own. Nothing this project's provenance envelope says applies to the partner's rows, and vice versa.
2. Minimum data walk
Step 1 — resolve the address to a point and a government. Geocode the address, then place the coordinate. Ambiguous candidates in different governments stop the walk, as in [[whose-government]]: screening the wrong point is worse than not screening.
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 First seen · 150 lines · 106 tokens per session scan A e046a09b17ee
federal-site-screen is a skill published in the GitHub repository pranava0x0/Commonwealth-MCP (0 stars, last pushed today), licensed Apache-2.0. It adds 106 tokens to every session and 1,758 once invoked, about $0.0005 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 2026-09-10.
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.
open-map-stack
Use textual agent instructions for GIS and geospatial work: source discovery and provenance, vector/raster/point-cloud pipelines, CRS and metric analysis, spatial SQL, routing and isochrones, QGIS projects, tile generation, and web maps. Use advanced tools and formats such as OSM, Overture, STAC, Sentinel/Landsat…
swmm-calibration
Calibration and validation scaffold for EPA SWMM. Use when an agent needs to (1) compare simulated vs observed flow, (2) evaluate candidate parameter sets, (3) rank explicit candidates by an objective, (4) run a bounded random / LHS / adaptive search for the best-fitting parameters, (5) run a publication-grade SCE-UA…
swmm-gis
GIS/DEM preprocessing for SWMM experiments using the user's own QGIS/GRASS layers. Use when the user asks to (1) delineate subcatchments through QGIS/GRASS (standard or entropy-guided), (2) preprocess QGIS-derived subcatchment polygons into builder-ready CSV, (3) identify high-entropy hotspot subcatchments, or (4)…
swmm-anywhere
Synthesize a plausible SWMM drainage network from public data (OSM streets + DEM) when NO real pipe-network data exists — input is just a bbox. Use ONLY when the user has no pipe shapefile/CAD/GIS data, or to establish a baseline before real data arrives; if real pipe data exists, route to swmm-network or swmm-gis…
swmm-builder
Assemble a runnable SWMM INP deterministically from subcatchment geometry/attributes, merged parameter JSON, network JSON, and climate references. Use when creating auditable INP + manifest artifacts for downstream swmm-runner/calibration.