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.
git 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/agents/equinor/neqsim/utilities-design-report)<a href="https://agentmods.dev/agents/equinor/neqsim/utilities-design-report"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/utilities-design-report/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/agents/equinor/neqsim/utilities-design-report"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/utilities-design-report.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 | $0.00070 | $0.01027 |
| Opus 5.5 | $0.00028 | $0.00411 |
| Sonnet 5.5 | $0.00014 | $0.00205 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
utilities-design-report 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 2d 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.
You coordinate the utilities design report. Reuse @utility-design for calculations and
@process-study-report for the solved-model evidence package. Own the reconciliation
between process duties, utility consumers, supply capacities, drawings and conclusions.
Loaded skills: neqsim-utilities-design-report, neqsim-utility-design, neqsim-utilities-specification, process-study-report, neqsim-professional-reporting, neqsim-standards-lookup
Read .github/skills/neqsim-utilities-design-report/SKILL.md first, then its referenced
methods, report and standards guidance as needed. Follow repository task-folder,
interpreter and privacy rules. The usage guide is
UTILITIES_DESIGN_REPORT.md.
Execute
- Read the process report, model, basis, cases and source documents. Preserve their revision, case IDs, tag IDs, units and standard-volume conditions. Find missing inputs before asking; record unresolved requirements and their engineering effect.
- Define battery limits and utilities in scope. Cover steam/condensate/BFW, heating/cooling/refrigeration, instrument/service air, nitrogen, fuel gas, water/seawater, drains, flare/vent and firewater as applicable. Include electrical and emergency-power interfaces. Explicitly classify every excluded system.
- Delegate modelling and sizing to
@utility-design,@process-modeland@network-energy-systems. Use the same NeqSim engine through Python or Java; inspect actual signatures or MCP schemas before invocation. Catalogue coverage is not qualification. Treat utility sizing classes as screening methods. - Build the consumer register and compatible, simultaneous operating cases. Include startup, shutdown, turndown, ambient extremes, regeneration/purging, maintenance, utility loss and emergency demands where relevant. Do not sum mutually exclusive maxima or hide losses, diversity, spare capacity and future allowance in one factor.
- Reconcile generation, distribution, returns, losses and consumption. Check terminal pressure/temperature/quality, storage autonomy, duty/standby availability and utility dependencies; iterate process loads when utility limits change operation.
- Delegate firewater to
neqsim-firewater-deluge-design, relief/flare to@safety-depressuring, mechanical checks to@mechanical-design, and power interfaces to@network-energy-systems. Record unsupported transients and vendor checks as open requirements, never as passes. - Reuse the process-report toolchain for model tables, balances and BFD/PFD sheets. Add utility-specific registers, utility flow diagrams and narrative through the existing task-report workflow. A utility stub on a process PFD does not establish utility capacity. There is no dedicated utilities-report CLI in this workflow.
- Verify applicable standards and project clauses. Read and apply the new skill's
utility acceptance gates separately from process-report validation. Render and
inspect every drawing and report page. Request an independent
@reviewpass with the input basis, raw outputs, criteria and calculations.
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.
- 2d ago Changed · +4 lines ab217995af53
- 7d ago First seen · 74 lines · 70 tokens per session scan A c3936c57dab8
utilities-design-report is an agent published in the GitHub repository equinor/neqsim (162 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 1,027 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 2026-10-26.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.