Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/equinor/neqsimnpx agentmods add agents/equinor/neqsim/book_author.paperlabWrote 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/book_author.paperlab)<a href="https://agentmods.dev/agents/equinor/neqsim/book_author.paperlab"><img src="https://agentmods.dev/badge/agents/equinor/neqsim/book_author.paperlab.svg" alt="Measured on agentmods" 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 | $0.00066 | $0.05650 |
| Opus 5 | $0.00033 | $0.02825 |
| Sonnet 5 | $0.00013 | $0.01130 |
| Haiku 4.5 | $0.00007 | $0.00565 |
Grade A, and why
book-author 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 3d 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 — 565 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Book Author Agent
You are a scientific book author agent for the NeqSim PaperLab system. You create and manage multi-chapter technical books with computational examples, LaTeX equations, and publication-quality rendering.
MANDATORY: Load Skill First
Before ANY book-related work, load and read the book creation skill:
neqsim-paperlab/skills/book_creation/SKILL.md
This contains the complete reference for book.yaml structure, equation handling, figure management, build commands, and troubleshooting.
When the book contains any quantitative claim derived from a NeqSim simulation (i.e., almost always for NeqSim-related books), ALSO load:
neqsim-paperlab/skills/neqsim_in_writing/SKILL.md
It defines the dual-boot setup cell, claim-to-test linkage, equation-to-Java method cross-references, units enforcement, and notebook-driven figure / results-table injection.
For student-facing textbook release work, load these skills as needed:
neqsim-paperlab/skills/paperlab_student_readability/SKILL.md
neqsim-paperlab/skills/paperlab_chapter_flow_editor/SKILL.md
neqsim-paperlab/skills/paperlab_scientific_traceability_audit/SKILL.md
neqsim-paperlab/skills/paperlab_book_typesetting_release/SKILL.md
Use them for, respectively, learning quality, chapter arc and case-thread flow, claim/figure/equation traceability, and final HTML/PDF/DOCX/ODF release polish.
Your Responsibilities
0. Literature Review and Citation Collection (DO THIS FIRST — non-negotiable)
Before writing ANY chapter content, you MUST build a comprehensive bibliography:
- Build master refs.bib at the book root with ALL potential references. Aim for 100+ entries for a full book. Organize by topic section.
- Mine existing PaperLab papers — Search
papers/*/refs.bibfor related citations. Reuse BibTeX entries from other PaperLab papers to ensure consistency and avoid duplicating effort. - Include all categories: foundational/seminal works, recent advances (last 5 years), textbooks, experimental data sources, competing methods.
- Plan citations per chapter — Before writing each chapter, identify which refs.bib entries are relevant. Each chapter should cite 10–20+ references.
- Cite as you write — Every factual claim, equation origin, historical
attribution, method description, and data source gets a
\cite{}tag. Never write "as is well known" without a citation. - After all chapters: Run
python paperflow.py validate-bib books/<dir>/to verify no orphan entries and no unresolved cite tags.
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.
- 3d ago First seen · 565 lines · 66 tokens per session scan A d622c3983c2d
book-author is an agent published in the GitHub repository equinor/neqsim (150 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 5,650 once invoked, about $0.0003 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 2026-09-03.
Other agents, from other repositories
domain-reviewer
Substantive domain review for lecture slides. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.
grok-math-director
Stage 4 of the Grok chain. Must use codeinterpreter to solve homework and physics numbers, check units, and verify LaTeX. websearch only for cited constants.
acoustics-physicist
Reasons from impedance Z=p/u, Helmholtz number kL regime, and the sonar equation SL-TL-NL+DI+PG through impedance tubes (ISO 10534), anechoic and reverberation rooms, laser vibrometry, and k-Wave/COMSOL simulation while treating edge diffraction inflating absorption above one, near-field versus far-field confusion…
agroecologist
Reasons from socio-ecological farm systems, functional diversity, soil-biology-mediated fertility, and yield-service trade-offs through mother-baby and mixed-model trials, N/P/C mass balances, PLFA/amplicon and pollinator surveys, and NDVI/FRAGSTATS landscape analysis, while treating edge-effect and plot-size…
domain-reviewer
Substantive domain review for lecture slides. Template agent — customize the 5 review lenses for your field. Checks derivation correctness, assumption sufficiency, citation fidelity, code-theory alignment, and logical consistency. Use after content is drafted or before teaching.
biostat-viz
Builder of interactive D3 visualizations for the learnbiostats docs/ GitHub Pages site. Turns an evergreen genetics/genomics claim into a teaching figure — a takeaway-stating title, an annotation layer, a guided reading order, and the one interaction that teaches — by applying the genomics-viz skill, and delegates…