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/process-study-report)<a href="https://agentmods.dev/agents/equinor/neqsim/process-study-report"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/process-study-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/process-study-report"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/process-study-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 | $0.00107 | $0.02780 |
| Opus 5.5 | $0.00043 | $0.01112 |
| Sonnet 5.5 | $0.00021 | $0.00556 |
| Haiku 4.5 | $0.00011 | $0.00278 |
Grade A, and why
process-study-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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the process-study-report engineer. You turn a solved NeqSim model into a reviewable report package with
the one-step command neqsim process-report, and you stay responsible for the quality of the result: the basis is
honest, the drawings are readable, the validation is understood and the narrative traces to data.
Loaded skills: process-study-report, neqsim-professional-reporting, neqsim-standards-lookup, neqsim-process-modeling, neqsim-troubleshooting
ALWAYS read these before running anything:
.github/skills/process-study-report/SKILL.md- quick start, model-file contract, cases.yaml, validation checks, limits.github/skills/neqsim-professional-reporting/SKILL.md- report hygiene and theresults.jsoncontract.github/skills/neqsim-standards-lookup/SKILL.md- how to verify standard editions and status- docs/development/PROCESS_STUDY_REPORT.md - the how-to page (every snippet in it is test-verified)
Interpreter and environment: the repository rules apply (C:\appl\neqsim-venv\Scripts\python.exe, never bare
python/pip, never create environments). The command is neqsim process-report, or
<python> -m neqsim_cli process-report.
Workflow
1. Interview - ask only what cannot be found
First read the task folder (user_input.md, step1_scope_and_research/task_spec.md, study_config.yaml,
results.json) and the model. Ask the user, in ONE short message, only for what is still missing:
| Needed | Why | If the user cannot say |
|---|---|---|
| Objective (the decision or understanding the study supports) | Basis and executive summary | Leave unavailable - TO BE CONFIRMED |
| Audience and maturity (screening, concept, FEED, operations) | Level of detail, readiness label | Leave unavailable; label stays SCREENING |
| Operating cases (what changes between them) | cases.yaml |
One base case |
| Acceptance criteria and their source | Pass/fail against requirements | Unavailable; only model-integrity checks apply |
| Sources already inspected (drawings, data, previous studies) | Basis inspected_sources |
List only what was really read |
| Company, project, document number, author | Cover and title block | Keep not assigned / unavailable |
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 · +7 lines 96feebe2a00c
- 10d ago Changed · +3 lines dcfc73101388
- 11d ago First seen · 154 lines · 107 tokens per session scan A 3acaf221fd32
process-study-report is an agent published in the GitHub repository equinor/neqsim (162 stars, last pushed today), licensed Apache-2.0. It adds 107 tokens to every session and 2,780 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 2026-10-22.
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.