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/yushui2022/MathModel-Skillnpx agentmods add skills/yushui2022/mathmodel-skill/paper-workflow-orchestratorWrote 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/yushui2022/mathmodel-skill/paper-workflow-orchestrator)<a href="https://agentmods.dev/skills/yushui2022/mathmodel-skill/paper-workflow-orchestrator"><img src="https://agentmods.dev/badge/skills/yushui2022/mathmodel-skill/paper-workflow-orchestrator.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00050 | $0.01388 |
| Opus 5 | $0.00025 | $0.00694 |
| Sonnet 5 | $0.00010 | $0.00278 |
| Haiku 4.5 | $0.00005 | $0.00139 |
Grade A, and why
paper-workflow-orchestrator 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MathModel Standard Orchestrator
Use this skill as the only entry router for a complete competition-paper task. Standard targets strong models that can maintain a long evidence chain and execute tools reliably while keeping cost controlled. It does not use Pro multi-agent tournaments or approval checkpoints.
Start Or Resume
From the contest project root, run:
python .claude/skills/paper-workflow-orchestrator/scripts/preflight_check.py
python .claude/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --status
Read paper_output/qa/workflow_guard_report.json and follow recommended_skill plus next_action. The current files and hashes override conversational memory.
Do not run downstream skills before their guard requirement passes. After a child skill finishes, return here and evaluate status again.
S0-S8
S0 Input Admission
preflight_check.py inventories problem_files/, hashes every input, checks runtime dependencies, prepares paper_output/, and rejects mixed MathModel editions. Required outputs:
paper_output/preflight_report.jsonpaper_output/input_manifest.jsonpaper_output/OUTPUT_LAYOUT.md
S1 Problem Analysis
Use $problem-doc-model-selector to create paper_output/step1/problem_analysis.json. Every question, attachment, field, objective, constraint, ambiguity, and required output must be traceable.
S2 Model And Rubric Route
Use $modeling-paper-rubric-and-model-selector. Produce:
paper_output/plan/model_route.jsonpaper_output/plan/rubric_alignment.jsonpaper_output/plan/scoring_strategy.md
Use $authoritative-data-harvester only when public external data is necessary. Keep source identity and retrieval notes.
S3 Data And Visualization Plan
Use $data-cleaning-and-visualization. Read only files classified in the input manifest and produce a fresh load report, data plan, visualization plan, figure index, and cleaned data. Contest-specific code belongs under paper_output/code/, never inside installed skills.
What ships with it
7 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.
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 f749a183cf3d
- 4d ago Changed · -161 lines · -14 tokens per session b8d3cbf8edd5
- 9d ago First seen · 302 lines · 64 tokens per session scan A ebe38aa98042
paper-workflow-orchestrator is a skill published in the GitHub repository yushui2022/MathModel-Skill (384 stars, last pushed today), licensed MIT. It adds 50 tokens to every session and 1,388 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 2026-08-30.
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…