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 pnnl/nepa-mcp --skill nepa-screeninggit clone --depth 1 https://github.com/pnnl/nepa-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/pnnl/nepa-mcp/nepa-screening)<a href="https://agentmods.dev/skills/pnnl/nepa-mcp/nepa-screening"><img src="https://agentmods.dev/badge/skills/pnnl/nepa-mcp/nepa-screening/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/pnnl/nepa-mcp/nepa-screening"><img src="https://agentmods.dev/badge/skills/pnnl/nepa-mcp/nepa-screening.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 | $0.00038 | $0.01041 |
| Opus 5 | $0.00019 | $0.00521 |
| Sonnet 5 | $0.00008 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
nepa-screening 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NEPA Screening
Use this skill for NEPA or ESA screening, environmental review scoping, project-area baseline research, jurisdictional context, or environmental regulatory lookup.
Establish the project area
Before location-scoped calls, confirm or derive latitude, longitude, and buffer distance in miles. Use gis tools to summarize the ROI, return GeoJSON, or calculate area. Use tigerweb_counties for intersecting counties and tribal for AIANNHA tribal lands.
Select authoritative datasets
- Use
censusfor ACS socioeconomic indicators. - Use
ipacfor USFWS species, critical habitat, migratory birds, wetlands, refuges, hatcheries, and related resources. - Use
esa_rangesfor NOAA ESA-listed species ranges. - Use
noaafor NOAA West Coast critical habitat. - Use
efhfor Essential Fish Habitat and Habitat Areas of Particular Concern. - Use
pcsrffor NOAA species ranges, critical habitat, salmon EFH/HAPC, and recovery projects. - Use
gbiffor biodiversity occurrences and county species lists. - Use
fema_nfhlfor flood zones, levees, water areas, and flood-risk summaries. - Use
epa_aqsfor air monitors, annual air-quality data, and NAAQS screening context. - Use
nepa_assistfor EPA NEPAssist screening categories. - Use
nrcs_soilsfor SSURGO soil map units, drainage and hydrologic-group indicators, restrictive layers, erosion factors, and farmland classifications. Treat results as soil-survey screening, not geotechnical advice, wetland delineation, infiltration testing, or an agency farmland determination. - Use
epa_acresfor identifiable EPA ACRES Brownfields property records; treat results as grant-reported screening data, not a complete contaminated-site inventory. Dense results are nearest-first and paginated; follow the returnedresult_offsetinstruction when the complete property list is needed. - Use
padusfor protected areas, ownership, management, and conservation status. - Use
blmfor BLM land use plans, wilderness areas, and national monuments. - Use
blm_mlrsfor BLM land-use authorization cases, locatable-mineral operations, and geothermal or oil-and-gas leases. Preserve the source disposition and treat mapped records as legal-description-derived screening evidence, not surveyed footprints, title opinions, or proof that an operation is active or authorized. - Use
usacefor Corps districts and wetland delineation regions. - Use
nrhpfor National Register of Historic Places properties. - Use
cfrfor current eCFR text, regulatory history, Federal Register citations, and executive orders.
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.
- 3d ago Changed · +10 lines 4af642e85c66
- 10d ago First seen · 68 lines · 38 tokens per session scan A f7ff17a4d600
nepa-screening is a skill published in the GitHub repository pnnl/nepa-mcp (13 stars, last pushed 2d ago), licensed BSD-3-Clause. It adds 38 tokens to every session and 1,041 once invoked, about $0.0002 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.
Other skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…