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 chengziyue1222/math-model-agent --skill write-model-papergit clone --depth 1 https://github.com/chengziyue1222/math-model-agentWrote 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/chengziyue1222/math-model-agent/write-model-paper)<a href="https://agentmods.dev/skills/chengziyue1222/math-model-agent/write-model-paper"><img src="https://agentmods.dev/badge/skills/chengziyue1222/math-model-agent/write-model-paper.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 | $0.00042 | $0.00803 |
| Opus 5 | $0.00021 | $0.00402 |
| Sonnet 5 | $0.00008 | $0.00161 |
| Haiku 4.5 | $0.00004 | $0.00080 |
Grade A, and why
write-model-paper 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 8d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Model Paper
Write the paper a contest reader sees: mathematical reasoning, evidence, figures and readable pages. Evidence checks protect the draft backstage; they must not turn the paper into an engineering log.
Workflow
- Confirm the contest template, problem source, model-selection rationale, results, figures, validation evidence and citations. Do not draft numbers, references or claims that lack a source.
- Read
references/paper-generation-guide.md,references/paper-structure.mdandconfig/paper_style.yamlat the repository root. Use the contest template if it overrides these defaults. - Draft an abstract that fits one page: problem essence and overall framework, then each question's method, decisive result and necessary validation; end with a short scope statement and 4--7 keywords.
- Build the paper in the canonical order: abstract, keywords, contents, restatement, analysis, assumptions, notation, conditional unified model, each question's model/solution/results, validation and sensitivity, evaluation, references and appendix.
- Add a unified-model section only when upstream dependency analysis establishes a shared core. Otherwise make the separate routes clear rather than forcing a formal common layer.
- For every formula, write purpose before it and definitions, computation and validity after it. For every result, write result, pattern, mechanism, evidence and implication; include limitations where they affect a decision.
- Use figures and three-line tables as evidence, not decoration. Put a table title above the table; retain representative rows in the body and move exhaustive data to an attachment.
- Cite only sources actually needed for methods, non-original theorems or external facts. Put references and appendix on separate pages; organize key appendix code by module at readable size.
- Render and visually inspect the PDF. Check title/heading hierarchy, no top-left running header, natural body pagination, orphan headings, figure readability, table width, bibliography page and appendix/code legibility.
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 254 B
- assets/cume-template.tex 11 KB
- references/paper-generation-guide.md 2.3 KB
- references/paper-structure.md 2.0 KB
- references/rule-pack-integration.md 672 B
- scripts/docx_png_figures.lua 585 B
- scripts/execute_skill.py 231 B runs code
- scripts/format_cumcm_docx.py 9.5 KB runs code
- scripts/render_template_preview.py 3.7 KB runs code
- scripts/set_docx_body_restart.ps1 1.5 KB runs code
- scripts/validate_cumcm_layout.py 2.4 KB runs code
- scripts/write_process_competition_paper.py 27 KB runs code
- scripts/write_supplier_competition_paper.py 32 KB runs code
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.
- 8d ago First seen · 48 lines · 42 tokens per session scan A cef00814daf0
write-model-paper is a skill published in the GitHub repository chengziyue1222/math-model-agent (16 stars, last pushed 28d ago), licensed MIT. It adds 42 tokens to every session and 803 once invoked, about $0.0002 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 skills, from other repositories
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
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.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
mapping-to-snomed
Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…