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-brazil-offshore-infrastructure-marketgit 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-brazil-offshore-infrastructure-market)<a href="https://agentmods.dev/skills/equinor/neqsim-community-skills/neqsim-brazil-offshore-infrastructure-market"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-brazil-offshore-infrastructure-market/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-brazil-offshore-infrastructure-market"><img src="https://agentmods.dev/badge/skills/equinor/neqsim-community-skills/neqsim-brazil-offshore-infrastructure-market.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 | $0.00095 | $0.02654 |
| Opus 5.5 | $0.00038 | $0.01062 |
| Sonnet 5.5 | $0.00019 | $0.00531 |
| Haiku 4.5 | $0.00010 | $0.00265 |
Grade A, and why
neqsim-brazil-offshore-infrastructure-market 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Brazil Offshore Infrastructure and Market
Use this skill to state what is public, what is UNKNOWN and how big the gas and host effects are, before they enter a Brazilian block evaluation. The packaged data is a snapshot of 2026-10-14 and goes stale.
When to Use
- A Brazilian pre-salt block or tie-back needs gas export routes, plants, tariffs, gas quality or market context.
- A report must separate public facts from declared assumptions and list every UNKNOWN.
- A host FPSO's capacity must be checked for a tie-back, including a gas-handling limit.
Inputs
- Declared gas CO2 (mol %), GOR (Sm3/Sm3), recoverable oil volume (MMbbl), export fraction, city-gate price.
- Host nameplate, host demand and, if known, the oil rate at which host compression limits (kbbl/d).
- Entry name for dataset lookups (for example
Rota 3,Bacalhau).
Outputs
- Dataset entries with value, unit,
source_id, confidence (official,company,press,estimate,declared,UNKNOWN) andas_of. - CO2 removal fraction, wellhead net-back, gas export revenue and share of oil revenue, host ullage and binding constraint.
- The explicit list of UNKNOWN entries to quote in the report.
Engineering Method
Source-id convention: INF-S<n> for the infrastructure file and MKT-S<n> for the market file; sources() resolves each id to a URL. null value or confidence UNKNOWN is a gap, never zero.
Routes and plants
- Rota 1 (Tupi to Mexilhao to UTGCA Caraguatatuba): 10 MMm3/d, about 359 km, since 2011. Rota 2 (to UTGCAB Cabiunas): 20 MMm3/d, 401 km, 24 in, since 2016 (official). Rota 3 (to Boaventura/GASLUB Itaborai): 18 MMm3/d, 355 km, commercial from Sep-Nov 2024.
- Rota 4A/4B (Cosan/Compass, about 21 MMm3/d): proposed, start year UNKNOWN, outside the EPE PDE 2035 base case. Planned export pipelines in EPE: Raia (16 MMm3/d, 2028; about 200 km to Cabiunas per the Equinor record) and SEAP (18 MMm3/d, 2030-32). Rota 5/6/SPA: UNKNOWN.
- Plants: UTGCAB Cabiunas 25.2 MMm3/d, Boaventura 21 MMm3/d (two modules), UTGCA capacity UNKNOWN, national fleet 120.1 MMm3/d (about 90 % Petrobras). Spare capacity per route and plant: UNKNOWN.
- Bacalhau FPSO: 220 kbopd, 530 MMscfd (about 15 MMm3/d) gas handling, no export pipeline in Phase 1 (associated gas re-injected); Phase 2 pipeline route UNKNOWN.
What ships with it
9 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/gas_export_screen.py 866 B runs code
- pyproject.toml 695 B
- README.md 998 B
- src/brazil_offshore_infrastructure_market/__init__.py 789 B runs code
- src/brazil_offshore_infrastructure_market/data.py 3.6 KB runs code
- src/brazil_offshore_infrastructure_market/data/brazil_gas_infrastructure.json 23 KB
- src/brazil_offshore_infrastructure_market/data/brazil_market_analogues.json 42 KB
- src/brazil_offshore_infrastructure_market/helpers.py 4.6 KB runs code
- tests/test_brazil_offshore_infrastructure_market.py 4.1 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 Changed · +8 lines f3996e447877
- 22d ago First seen · 126 lines · 95 tokens per session scan A 11bfcd259e05
neqsim-brazil-offshore-infrastructure-market is a skill published in the GitHub repository equinor/neqsim-community-skills (4 stars, last pushed today), licensed Apache-2.0. It adds 95 tokens to every session and 2,654 once invoked, about $0.0004 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 2026-10-16.
neqsim-brazil-offshore-infrastructure-market compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| neqsim-brazil-offshore-infrastructure-marketequinor/neqsim-community-skills | Skill | 4 | today | Apache-2.0 | A | 95 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 35k | 3d 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 |