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 albert-hofmangit 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/albert-hofman)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/albert-hofman"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/albert-hofman/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/albert-hofman"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/albert-hofman.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 | $0.00093 | $0.01024 |
| Opus 5 | $0.00046 | $0.00512 |
| Sonnet 5 | $0.00019 | $0.00205 |
| Haiku 4.5 | $0.00009 | $0.00102 |
Grade A, and why
albert-hofman 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 11d 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 Albert Hofman
Albert Hofman is a pioneering clinical epidemiologist known for architecting massive, decades-long population cohorts like the Rotterdam Study. His signature thinking shifts the focus of chronic disease from late-stage, individual clinical treatment to lifelong, population-level prevention. He views aging not as a decline that begins in the elderly, but as a lifelong process whose foundations are laid in childhood and even in utero.
Reach for this skill whenever you are designing public health interventions, evaluating the predictive power of medical screenings, or analyzing the trajectory of cardiovascular and neurodegenerative diseases.
Core principles
- Life-Course Approach to Healthy Ageing: Healthy ageing research and interventions must include younger populations and start in childhood, because the ageing process begins much earlier than old age.
- Population-Level Interventions Over Individual Screening: For early-life risk factors, shifting the overall risk distribution through environmental modifications is more effective than individual screening, because physiological metrics only track moderately over time.
- Prevention of Neurological Diseases in the Elderly: Cognitive decline and related conditions are not strictly inevitable; there is great potential to prevent or postpone them.
- Age-Adjusted Predictive Power of Risk Factors: Traditional cardiovascular risk factors weaken in elderly populations, necessitating supplementary diagnostic methods like coronary calcification scoring.
- Interplay of Vascular, Genetic, and Aging Factors: Multifactorial chronic diseases must be understood holistically, as seemingly unrelated conditions often share underlying pathways.
For detailed rationale and quotes, see references/principles.md.
How Albert Hofman reasons
Hofman reasons in distributions and decades. When evaluating a health risk, he first asks about its Tracking (Distribution Stability)—whether an individual's relative position within a population remains stable over time. If a metric like childhood blood pressure only tracks moderately, he dismisses individual screening in favor of population-wide environmental changes.
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 8.8 KB
- _workspace/clustered_corpus.e584bd6c.json 13 KB
- _workspace/discovery/books.json 7.2 KB
- _workspace/discovery/essays.json 8.7 KB
- _workspace/discovery/frameworks.json 11 KB
- _workspace/discovery/interviews.json 7.7 KB
- _workspace/discovery/letters.json 7.8 KB
- _workspace/discovery/papers.json 6.8 KB
- _workspace/discovery/podcasts.json 7.1 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 24 KB
- _workspace/discovery/talks.json 5.9 KB
- _workspace/distilled/src_000.e584bd6c.json 385 B
- _workspace/distilled/src_001.e584bd6c.json 459 B
- _workspace/distilled/src_002.e584bd6c.json 418 B
- _workspace/distilled/src_003.e584bd6c.json 441 B
- _workspace/distilled/src_004.e584bd6c.json 427 B
- _workspace/distilled/src_005.e584bd6c.json 438 B
- _workspace/distilled/src_006.e584bd6c.json 416 B
- _workspace/distilled/src_007.e584bd6c.json 445 B
- _workspace/distilled/src_008.e584bd6c.json 437 B
- _workspace/distilled/src_009.e584bd6c.json 477 B
- _workspace/distilled/src_010.e584bd6c.json 456 B
- _workspace/distilled/src_014.e584bd6c.json 511 B
- _workspace/distilled/src_030.e584bd6c.json 397 B
- _workspace/distilled/src_036.e584bd6c.json 2.4 KB
- _workspace/distilled/src_037.e584bd6c.json 507 B
- _workspace/distilled/src_038.e584bd6c.json 433 B
- _workspace/distilled/src_039.e584bd6c.json 3.4 KB
- _workspace/distilled/src_051.e584bd6c.json 2.1 KB
- _workspace/distilled/src_052.e584bd6c.json 502 B
- _workspace/distilled/src_054.e584bd6c.json 2.7 KB
- _workspace/distilled/src_055.e584bd6c.json 2.7 KB
- _workspace/distilled/src_058.e584bd6c.json 644 B
- _workspace/distilled/src_059.e584bd6c.json 600 B
- _workspace/distilled/src_065.e584bd6c.json 552 B
- _workspace/distilled/src_066.e584bd6c.json 486 B
- _workspace/raw/src_000.json 5.6 KB
- _workspace/raw/src_001.json 16 KB
- _workspace/raw/src_002.json 3.1 KB
- _workspace/raw/src_003.json 5.4 KB
- _workspace/raw/src_004.json 12 KB
- _workspace/raw/src_005.json 27 KB
- _workspace/raw/src_006.json 22 KB
- _workspace/raw/src_007.json 48 KB
- _workspace/raw/src_008.json 9.1 KB
- _workspace/raw/src_009.json 13 KB
- _workspace/raw/src_010.json 4.5 KB
- _workspace/raw/src_014.json 5.4 KB
- _workspace/raw/src_030.json 1.4 KB
- _workspace/raw/src_036.json 15 KB
- _workspace/raw/src_037.json 674 B
- _workspace/raw/src_038.json 10 KB
- _workspace/raw/src_039.json 15 KB
- _workspace/raw/src_051.json 11 KB
- _workspace/raw/src_052.json 10 KB
- _workspace/raw/src_054.json 29 KB
- _workspace/raw/src_055.json 12 KB
- _workspace/raw/src_058.json 11 KB
- _workspace/raw/src_059.json 28 KB
- _workspace/raw/src_065.json 12 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.
- 11d ago First seen · 52 lines · 93 tokens per session scan A ba5653091a96
albert-hofman is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 23d ago), licensed MIT. It adds 93 tokens to every session and 1,024 once invoked, about $0.0005 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…