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-setupgit 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-setup)<a href="https://agentmods.dev/skills/equinor/neqsim/neqsim-setup"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-setup/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-setup"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/neqsim-setup.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 | $0.00113 | $0.02374 |
| Opus 5.5 | $0.00045 | $0.00950 |
| Sonnet 5.5 | $0.00023 | $0.00475 |
| Haiku 4.5 | $0.00011 | $0.00237 |
Grade A, and why
neqsim-setup 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 20d 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
NeqSim setup (/neqsim-setup)
Walk the user through the three user-level settings the task workflow depends
on, then run neqsim doctor. Everything here is stored in
~/.neqsim/task_defaults.json, so it is shared by the workspace checkout, the
pip-installed toolkit and the agent plugin.
0. Find the CLI
Run neqsim --show-task-root. If the shell says neqsim is not recognized,
use <python-executable> -m neqsim_cli --show-task-root where
<python-executable> is NEQSIM_PYTHON if set, else the first python3 /
py -3 / python on PATH. Use that same form for every command below. If
neither works the toolkit is not installed yet. In a plugin install the
SessionStart hook installs it in the background on the first prompt of a
session; check ~/.neqsim/plugin-install/neqsim/install.log (last line
== ... OK or == ... FAILED with the pip error above it). If the log is
missing or failed, install by hand from the plugin's vendored copy:
<python-executable> -m pip install "<plugin folder>/toolkit" where the
plugin folder is
%USERPROFILE%\.vscode\agent-plugins\github.com\equinor\neqsim-copilot-plugin\neqsim
on Windows (~/.vscode/agent-plugins/... on Linux and macOS). A marketplace
install lands there, not under agentPlugins in the VS Code user-data
folder — that one only holds synced customization plugins, so do not conclude
from its absence that the plugin is not installed. A Copilot CLI install lands
in ~/.copilot/installed-plugins/neqsim-copilot-plugin/<plugin>. Without a
plugin:
<python-executable> -m pip install "neqsim-dev-setup @ git+https://github.com/equinor/neqsim.git#subdirectory=devtools".
Installing the toolkit also pip-installs the neqsim PyPI package (the packaged
JAR + jpype bridge), and the hook's own install.log runs IMPORT_OK=1 IMPORT_FAILED=0 against it afterwards, so a plugin-only install always ends up
with the full NeqSim Python API importable — not just the CLI.
The neqsim-community and neqsim-enterprise plugins install their skill
packages through the same hook, into the same interpreter:
~/.neqsim/plugin-install/<plugin>/install.log. A healthy log ends with
live dependencies: all N installed, IMPORT_OK=<n> IMPORT_FAILED=0 and
== ... OK. Each FAILED <package> (<error>) line names a skill package that
does not import and why — most often a missing live dependency
(ModuleNotFoundError: stidapi, eq_api_connector, msal_bearer, pepr_client,
tagreader), which means the STID / SAP-Maintenance / PDM / PEPR / historian
agents cannot reach their systems. Fix by hand with
<python-executable> -m pip install -e "<plugin folder>/neqsim-enterprise" --no-deps
followed by
<python-executable> -m pip install -r "<plugin folder>/neqsim-enterprise/requirements-live.txt"
(add --no-index --find-links "<plugin folder>/neqsim-enterprise/wheels" for an
offline bundle). A missing log means the hook never ran for that plugin: start a
new chat, then check the plugin version against these known hook failures —
all fixed by updating the plugin:
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.
- 20d ago Changed · -50 tokens per session 99959f186001
- 24d ago Changed · +15 lines a5abfec1ac76
- 25d ago Changed · +1 lines dfe5bc1f954b
- 26d ago Changed · +12 lines 19d5b317aab9
- 27d ago First seen · 98 lines · 163 tokens per session scan A b142bb7da2bd
neqsim-setup is a skill published in the GitHub repository equinor/neqsim (156 stars, last pushed today), licensed Apache-2.0. It adds 113 tokens to every session and 2,374 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 2026-09-20.
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…
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.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…