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 agentmods add agents/equinor/neqsim/solve.taskgit clone --depth 1 https://github.com/equinor/neqsimWhat 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 | $0.00073 | $0.31143 |
| Opus 5 | $0.00036 | $0.15571 |
| Sonnet 5 | $0.00015 | $0.06229 |
| Haiku 4.5 | $0.00007 | $0.03114 |
Grade A, and why
solve engineering task 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 — 2,482 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ MANDATORY FIRST ACTION — CREATE TASK FOLDER (DO NOT SKIP)
Before writing ANY files, notes, notebooks, or analysis, you MUST do one of these:
- Resume request: If the user explicitly asks to resume an existing task,
read that task's
progress.json,README.md, andstudy_config.yamlfirst; do not create a duplicate folder. - New task: Otherwise create a task folder immediately.
For new tasks, make only the minimal mental classification needed to choose the
--type flag and a short title. Do not search, draft notes, or build a plan
before the folder exists.
- Run
neqsim new-task "TASK TITLE" --type X --author "Agent" --prompt "<verbatim user request>"in the terminal- Pass the user's original chat message verbatim via
--prompt(or use--prompt-file path.txtfor long inputs). - This populates
user_input.mdso the task can be reproduced later.
- Pass the user's original chat message verbatim via
- Confirm the folder
task_solve/YYYY-MM-DD_task_slug/was created - Read the generated
task_solve/YYYY-MM-DD_task_slug/README.md - Open
user_input.mdand verify section 1 contains the original prompt. If it is empty (e.g. you forgot--prompt), paste the verbatim user message there now.
ALL deliverables go inside this task_solve/ folder. The folder structure is:
task_solve/YYYY-MM-DD_task_slug/
├── README.md ← Update with results
├── user_input.md ← Verbatim user prompt + Q&A + follow-ups (REPRODUCIBILITY LOG)
├── results.json ← Save key results here
├── figures/ ← All PNG figures
├── step1_scope_and_research/
│ ├── task_spec.md ← Fill with scope, standards, criteria
│ ├── notes.md ← Research notes
│ ├── analysis.md ← Deep analysis (Design/Development)
│ ├── neqsim_improvements.md ← NIPs for gaps found
│ ├── document_evidence_manifest.json ← Per-file extraction coverage + evidence packages
│ └── references/ ← Reference documents (STID, PDFs, datasheets)
├── step2_analysis/
│ ├── *.ipynb ← Jupyter notebooks (main analysis)
│ ├── *.py ← Runner scripts for quick calculations
│ └── notes.md ← Validation notes
└── step3_report/
└── generate_report.py ← Report generator
If you skip this step, the entire workflow is broken. Do it NOW, before anything else.
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 First seen · 2,482 lines · 73 tokens per session scan A 0605465545fa
solve engineering task is an agent published in the GitHub repository equinor/neqsim (147 stars, last pushed 2d ago), licensed Apache-2.0. It adds 73 tokens to every session and 31,143 once invoked, about $0.0004 per session on Opus 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 agents, from other repositories
batch-processing-optimizer
Batch job and bulk operation optimization specialist.
Demonstrate
Agent for demonstrating VS Code features.
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.