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 --skill neqsim-capability-mapgit clone --depth 1 https://github.com/equinor/neqsimWrote 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/neqsim-capability-map)<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-capability-map"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-capability-map/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/neqsim-capability-map"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-capability-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00069 | $0.15818 |
| Opus 5.5 | $0.00028 | $0.06327 |
| Sonnet 5.5 | $0.00014 | $0.03164 |
| Haiku 4.5 | $0.00007 | $0.01582 |
Grade A, and why
neqsim-capability-map 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 today.
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 — 820 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NeqSim Capability Map
Structured reference of what NeqSim can do, organized by engineering discipline. Use this to quickly check if a capability exists before searching the source code.
Start with current source and deployed capabilities
Treat the tables below as navigation hints, not an exhaustive or qualified support list.
For any unfamiliar capability, first follow
the discovery contract.
In a checkout, run uv run --project devtools --locked devtools/capability_search.py "<need or API>" --json.
It searches current source types and public member names across all Java domains and returns
agent/skill entry points, documentation and bounded test references. Use --audit to check
package routing completeness. Source routing is distinct from the operation coverage registry.
With MCP, search the deployed artifact and inspect the exact API/schema before execution.
Read only the relevant sections and follow references; do not load this entire inventory for
every calculation. Recheck source, tests and runtime version before accepting a stated gap.
For measured agent/MCP coverage, inspect getCapabilities.engineeringCoverage
and use runCapability with action="coverage", view="capabilities" or
view="apis", a query and bounded pagination. Follow the returned tool, API,
skill and agent references; retrieve the schema and inspect setup before running.
Reuse the catalog digest across pages. Declared routes and source/test mentions
are not successful execution or engineering qualification. An unmapped API needs
review, not an automatic conclusion that it is unsupported. See
docs/development/ENGINEERING_CAPABILITY_COVERAGE.md for the evidence contract
and campaign #3153 completion gates.
Last updated: 2026-10-03 (section L lists the capability families that have a dedicated skill added in the 2026-10 audit)
A. Thermodynamic Models (Equations of State)
Cubic EOS
| Class | Fluid Type | Mixing Rule | Notes |
|---|---|---|---|
SystemSrkEos |
Dry/lean gas, simple HC | "classic" |
Most common choice |
SystemPrEos |
General HC, oil systems | "classic" |
Better liquid densities than SRK |
SystemPrEos1978 |
HC with Peng-Robinson 1978 | "classic" |
Updated alpha function |
SystemPrEosvolcor |
PR with volume correction | "classic" |
Volume-translated PR |
SystemSrkEosvolcor |
SRK with volume correction | "classic" |
Volume-translated SRK |
SystemSrkPenelouxEos |
SRK with Peneloux correction | "classic" |
Volume shift |
SystemSrkMathiasCopeman |
SRK + Mathias-Copeman alpha | "classic" |
Better vapor pressure fit |
SystemPrMathiasCopeman |
PR + Mathias-Copeman alpha | "classic" |
Better vapor pressure fit |
SystemSrkTwuCoonEos |
SRK + Twu-Coon alpha | "classic" |
TST-type alpha function |
SystemRKEos |
Redlich-Kwong (original) | "classic" |
Historical / teaching |
SystemPrDanesh |
PR-Danesh variant | "classic" |
Oil recovery applications |
SystemPsrkEos |
Predictive SRK (group contribution) | — | No BIPs needed for some systems |
SystemSrkSchwartzentruberEos |
SRK + Schwarzentruber-Renon | "classic" |
Polar compounds |
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.
- today Changed · +18 lines 499786e0acd6
- 2d ago Changed · +9 lines 2d09917e5b4b
- 20d ago Changed · +91 lines 6d4975fb98ce
- 1mo ago Changed · +17 lines 4b086dad761b
- 1mo ago First seen · 685 lines · 69 tokens per session scan A 6ff8c106f76d
neqsim-capability-map is a skill published in the GitHub repository equinor/neqsim (158 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 15,818 once invoked, about $0.0003 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.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.