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 K-Dense-AI/mimeographs --skill frank-b-hugit clone --depth 1 https://github.com/K-Dense-AI/mimeographsWrote 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/k-dense-ai/mimeographs/frank-b-hu)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/frank-b-hu"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/frank-b-hu/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/k-dense-ai/mimeographs/frank-b-hu"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/frank-b-hu.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00137 | $0.01187 |
| Opus 5 | $0.00068 | $0.00593 |
| Sonnet 5 | $0.00027 | $0.00237 |
| Haiku 4.5 | $0.00014 | $0.00119 |
Grade A, and why
frank-b-hu 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 12d 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Frank B. Hu
Frank B. Hu's thinking fundamentally shifts the lens of nutrition from isolated biochemical components to complex, real-world systems. As a nutrition epidemiologist, he recognizes that humans eat meals, not single nutrients, and that these dietary patterns interact synergistically to influence chronic disease risk. His approach bridges the gap between molecular biology, population health, and environmental sustainability.
Crucially, his reasoning extends beyond the plate. He views the modern food landscape as a "toxic obesogenic environment" where individual willpower is vastly outmatched by systemic forces, necessitating policy-level interventions. Reach for this skill whenever you're evaluating dietary advice, analyzing public health policies, discussing plant-based diets, or exploring the intersection of human longevity and planetary health.
Core principles
- Always Ask 'Compared to What?': The health effect of a food or nutrient can only be understood by looking at what it replaces in the diet, because dietary trade-offs drive metabolic outcomes.
- Focus on Overall Dietary Patterns: Nutritional epidemiology should examine the effects of the overall diet rather than just individual nutrients, because single components are difficult to isolate and fail to capture complex synergistic interactions.
- Not All Plant-Based Diets Are Healthy: Plant-based diets must be evaluated on their nutritional quality, not just the absence of animal products, because highly processed plant foods can increase chronic disease risk.
- Policy Over Individual Behavior: Individual behavior change is insufficient without policy intervention, because education cannot overcome an obesogenic environment dominated by cheap, ultra-processed foods.
- Human Health and Planetary Health are Interconnected: What is good for human longevity is generally good for the health of the planet, because traditional, plant-forward dietary patterns simultaneously reduce disease risk and environmental degradation.
What ships with it
60 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.
- _workspace/agents_output.e584bd6c.json 11 KB
- _workspace/clustered_corpus.e584bd6c.json 27 KB
- _workspace/discovery/books.json 11 KB
- _workspace/discovery/essays.json 11 KB
- _workspace/discovery/frameworks.json 4.6 KB
- _workspace/discovery/interviews.json 8.7 KB
- _workspace/discovery/letters.json 12 KB
- _workspace/discovery/papers.json 11 KB
- _workspace/discovery/podcasts.json 9.2 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 28 KB
- _workspace/discovery/talks.json 5.7 KB
- _workspace/distilled/src_000.e584bd6c.json 648 B
- _workspace/distilled/src_001.e584bd6c.json 508 B
- _workspace/distilled/src_002.e584bd6c.json 1.7 KB
- _workspace/distilled/src_004.e584bd6c.json 605 B
- _workspace/distilled/src_005.e584bd6c.json 7.1 KB
- _workspace/distilled/src_006.e584bd6c.json 1.7 KB
- _workspace/distilled/src_008.e584bd6c.json 1.5 KB
- _workspace/distilled/src_009.e584bd6c.json 6.6 KB
- _workspace/distilled/src_010.e584bd6c.json 6.9 KB
- _workspace/distilled/src_011.e584bd6c.json 6.9 KB
- _workspace/distilled/src_012.e584bd6c.json 437 B
- _workspace/distilled/src_015.e584bd6c.json 4.9 KB
- _workspace/distilled/src_016.e584bd6c.json 1.1 KB
- _workspace/distilled/src_017.e584bd6c.json 409 B
- _workspace/distilled/src_022.e584bd6c.json 6.3 KB
- _workspace/distilled/src_023.e584bd6c.json 623 B
- _workspace/distilled/src_030.e584bd6c.json 578 B
- _workspace/distilled/src_031.e584bd6c.json 3.4 KB
- _workspace/distilled/src_032.e584bd6c.json 1.3 KB
- _workspace/distilled/src_033.e584bd6c.json 771 B
- _workspace/distilled/src_034.e584bd6c.json 6.1 KB
- _workspace/distilled/src_035.e584bd6c.json 4.8 KB
- _workspace/distilled/src_036.e584bd6c.json 5.8 KB
- _workspace/distilled/src_037.e584bd6c.json 4.3 KB
- _workspace/distilled/src_038.e584bd6c.json 4.1 KB
- _workspace/raw/src_000.json 2.7 KB
- _workspace/raw/src_001.json 8.7 KB
- _workspace/raw/src_002.json 2.6 KB
- _workspace/raw/src_004.json 3.0 KB
- _workspace/raw/src_005.json 44 KB
- _workspace/raw/src_006.json 2.5 KB
- _workspace/raw/src_008.json 8.9 KB
- _workspace/raw/src_009.json 30 KB
- _workspace/raw/src_010.json 38 KB
- _workspace/raw/src_011.json 38 KB
- _workspace/raw/src_012.json 595 B
- _workspace/raw/src_015.json 46 KB
- _workspace/raw/src_016.json 5.3 KB
- _workspace/raw/src_017.json 6.4 KB
- _workspace/raw/src_022.json 21 KB
- _workspace/raw/src_023.json 4.1 KB
- _workspace/raw/src_030.json 2.1 KB
- _workspace/raw/src_031.json 10 KB
- _workspace/raw/src_032.json 10 KB
- _workspace/raw/src_033.json 20 KB
- _workspace/raw/src_034.json 16 KB
- _workspace/raw/src_035.json 15 KB
- _workspace/raw/src_036.json 51 KB
- _workspace/raw/src_037.json 52 KB
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.
- 12d ago First seen · 52 lines · 137 tokens per session scan A a69c221ff2d5
frank-b-hu is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 24d ago), licensed MIT. It adds 137 tokens to every session and 1,187 once invoked, about $0.0007 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…