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 equinor/neqsim-community-skills --skill neqsim-near-field-discoveriesgit clone --depth 1 https://github.com/equinor/neqsim-community-skillsWrote 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/equinor/neqsim-community-skills/neqsim-near-field-discoveries)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-near-field-discoveries"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-near-field-discoveries/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/equinor/neqsim-community-skills/neqsim-near-field-discoveries"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-near-field-discoveries.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 | $0.00115 | $0.02770 |
| Opus 5.5 | $0.00046 | $0.01108 |
| Sonnet 5.5 | $0.00023 | $0.00554 |
| Haiku 4.5 | $0.00012 | $0.00277 |
Grade A, and why
neqsim-near-field-discoveries 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 10d 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Near-Field Discoveries
A field-development evaluation is only as good as its knowledge of the neighbourhood: which discoveries lie near the target, which are already planned or approved, which are written off, who operates them, how big they are, and which host could serve several of them. This skill builds that picture from open data and draws it, for the Norwegian Continental Shelf (Sodir) and for Brazil (ANP).
It is a screening inventory. It does not hold licence, partner or reserve data that is not public, and it does not decide a concept.
When to Use
- A discovery, prospect or block needs "what is near me?" with status, operator, volumes and plans.
- A tie-back, stand-alone or area-development comparison needs the neighbouring discoveries that could share a host or change host ullage.
- A bid or concept study needs a map for a report (
neqsim-brazil-offshore-infrastructure-market,neqsim-psc-bid-economics-screening,neqsim-concept-longlist-shortlist-screening). - A task asks for a map of discoveries, fields, evaluation-plan areas, hosts and pipelines around a point.
Inputs
- Target
(lon, lat)in WGS84 / SIRGAS 2000 degrees, its name, and its source. A block centroid is not a well position: say so. - Radius in km (default 100 to 150 for tie-back screening; up to 250 km for pre-salt hosts).
- Country:
NO(Sodir) orBR(ANP). Both can be combined in one inventory for a cross-border view. - Optional: aliases (operator names for Brazilian discovery wells), volumes from a non-ANP source,
bathymetry grid, extra host lists, and extra records of kind
prospect(for example GeoX prospects or a user-supplied prospect list) that are drawn as triangles and counted apart from discoveries.
Outputs
Inventory.records: discoveries, fields and evaluation areas inside the radius, nearest first, each withstage,status_raw,hc_type,discovery_year,operator,distance_km,bearing, volumes with basis,plan_note,plan_flags, nearest hosts, source URL and an explicitgapslist.Inventory.summary(): counts and volume roll-up per stage;area_clusters(): open discoveries within 15 km of each other (joint-development candidates).- Files from
Inventory.write(folder): CSV, JSON, GeoJSON (loads in QGIS, ArcGIS and Omnia Maps as an overlay) and a Markdown note. plot_near_field(inv, "map.png", bathymetry=grid): map with stage colours, outlines, evaluation areas, hosts, pipelines, radius rings, labels and sources.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/near_field_study.py 2.9 KB runs code
- pyproject.toml 746 B
- README.md 1021 B
- src/near_field_discoveries/__init__.py 1.2 KB runs code
- src/near_field_discoveries/brazil.py 20 KB runs code
- src/near_field_discoveries/geo.py 7.6 KB runs code
- src/near_field_discoveries/inventory.py 15 KB runs code
- src/near_field_discoveries/mapping.py 9.0 KB runs code
- src/near_field_discoveries/models.py 4.6 KB runs code
- src/near_field_discoveries/ncs.py 17 KB runs code
- tests/test_brazil.py 6.1 KB runs code
- tests/test_inventory_map.py 4.0 KB runs code
- tests/test_ncs.py 5.1 KB runs code
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.
- 10d ago First seen · 168 lines · 115 tokens per session scan A e9faff3b5833
neqsim-near-field-discoveries is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 115 tokens to every session and 2,770 once invoked, about $0.0005 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 2026-10-28.
neqsim-near-field-discoveries compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-near-field-discoveriesequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 115 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |