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 5.5 | $0.00015 | $0.00416 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo ago Changed · +10 lines 4af642e85c66
- 2mo 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 (22 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 5.5. 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.
nepa-screening compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| nepa-screeningpnnl/nepa-mcp | Skill | 22 | 2d ago | BSD-3-Clause | A | 38 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 2d ago | Apache-2.0 | A | 123 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 83 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 44 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 56k | 4d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 33k | yesterday | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |