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 figure_discussiongit 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/figure_discussion)<a href="https://agentmods.dev/skills/equinor/neqsim/figure_discussion"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/figure_discussion/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/figure_discussion"><img src="https://agentmods.dev/badge/skills/equinor/neqsim/figure_discussion.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 | $0.00000 | $0.01843 |
| Opus 5 | $0.00000 | $0.00922 |
| Sonnet 5 | $0.00000 | $0.00369 |
| Haiku 4.5 | $0.00000 | $0.00184 |
Grade A, and why
figure_discussion 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 5d 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.
This is a copy
91% identical to figure-discussion — 25 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Figure Discussion (observation → mechanism → implication → recommendation)
When to Use
USE WHEN: writing the discussion of a figure in a paper, book chapter, or
task report. Every figure that appears in a deliverable MUST have an
accompanying discussion block that follows this contract. Loaded by
scientific-writer, book-author, narrative-framer, and the
solve.task.agent workflow.
DO NOT USE for: figure generation (use generate_publication_figures),
captions only (captions are a separate, terser artefact).
Core principle
A figure that appears in a deliverable without a corresponding discussion block is a wasted figure. Reviewers and readers should be able to read the figure → discussion pair and walk away knowing what the figure shows, why it shows that, what it means, and what to do about it, in that order, without having to reverse-engineer the conclusion from the plot.
This skill ports the contract from task_solve/ results.json
figure_discussion[] blocks to the paper / book authoring pipeline.
The four-part contract
Every figure discussion block has exactly four parts. Each is one to
three sentences. The block lives immediately after the figure in
the manuscript (paper.md or chapter.md) or in the corresponding
results.json field.
1. Observation — what the figure shows
State what the figure shows, with numbers. Do not describe the
plot ("a downward-sloping line"); describe the result ("the iteration
count drops from 28 to 16 as n_components increases from 4 to 12").
Rules:
- Always include at least one number with its unit.
- Always state the trend in scientific, not graphical, terms.
- Reference the figure number explicitly.
2. Mechanism — why it shows that
Explain the underlying physics, numerics, or algorithm. Tie back to an equation from the methods section or a NeqSim Java class.
Rules:
- Reference an equation by number (Eq. 7) or a Java class
(
SystemSrkEos). - One sentence on the dominant mechanism is enough; do not hand-wave with multiple competing explanations.
- If the mechanism is unclear, say so — do not invent one.
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.
- 5d ago First seen · 199 lines · 0 tokens per session scan A c713f9aaea0b
figure_discussion is a skill published in the GitHub repository equinor/neqsim (151 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,843 tokens. A static security scan graded it A with 0 findings. It is 91% identical to figure-discussion, differing in 25 lines, and is treated as a copy.
Other skills, from other repositories
pythermodb-reference-maker
Extract thermodynamic tables and correlations from references (CSV, PDF, images, or text) and convert them into the project's structured pyThermoDB YAML schema. Supports data tables, constants tables, matrix-parameter tables, and equation-based correlations (e.g., Cp, vapor pressure, density, enthalpy of…
seismic-interpretation
End-to-end seismic interpretation workflow from SEG-Y loading through signal processing, rock physics, and visualization. Use when working with seismic data analysis pipelines.
cantera-combustion
Use this Skill for combustion simulations with Cantera: mechanism loading, freely propagating flames, ignition delay, reactors, and sensitivity analysis.
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.