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-micro-unit-generatorWrote 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-micro-unit-generator)<a href="https://agentmods.dev/skills/yushui2022/mathmodel-skill/paper-micro-unit-generator"><img src="https://agentmods.dev/badge/skills/yushui2022/mathmodel-skill/paper-micro-unit-generator.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 | $0.00039 | $0.00993 |
| Opus 5 | $0.00019 | $0.00496 |
| Sonnet 5 | $0.00008 | $0.00199 |
| Haiku 4.5 | $0.00004 | $0.00099 |
Grade A, and why
paper-micro-unit-generator 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Paper Micro-Unit Generator
Use this skill only for local repair or an explicitly requested legacy scaffold. paper-formal-writer remains the sole formal author and the only producer of paper_output/final_paper_source.md and paper_output/final_paper.docx.
Entry Check
For formal repair, run:
python .claude/skills/paper-workflow-orchestrator/scripts/workflow_guard.py --skill paper-micro-unit-generator
Continue only when S0-S6 pass and paper_output/qa/repair_queue.json contains at least one item whose strategy is micro-repair. Do not create a repair queue manually to bypass the two-failure threshold.
Legacy and quickstart modes are installation or old-model scaffolds. They do not satisfy S7 and do not require the formal repair queue.
Formal Repair Mode
- Read
paper_output/plan/writing_plan.json,paper_output/context/authoring_state.json,paper_output/qa/draft_audit.json, andpaper_output/qa/repair_queue.json. - Select only queued
micro-repairitems. Keep the issue ID, section, failure category, expected evidence, and attempt count intact. - Read the affected section draft and only the evidence needed by that issue. Do not rewrite unrelated sections.
- Write repair material to
paper_output/drafts/repairs/<issue-id>.md. The material must contain concrete replacement text, its target location, and any required evidence marker. - Apply the replacement to the queued section draft. Preserve valid headings, equations, figure/table identifiers, citations, and evidence markers.
- Re-run the section audit:
python .claude/skills/paper-formal-writer/scripts/validate_authoring.py --section <section-id>
- Return to
$paper-formal-writeror$paper-workflow-orchestrator. This skill must not assemble the formal manuscript or generate Word.
If the same blocking category reaches the third changed attempt, respect authoring_state.status = BLOCKED. Report the evidence or requirement causing the failure and suggest Lite as a user decision; never switch editions automatically.
What ships with it
3 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.
- 3d ago Changed · -355 lines · -17 tokens per session fb1cf12fb229
- 7d ago First seen · 444 lines · 56 tokens per session scan A 5830d1ee58a1
paper-micro-unit-generator is a skill published in the GitHub repository yushui2022/MathModel-Skill (354 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 993 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…
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.
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…
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…