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 graham-a-colditzgit 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/graham-a-colditz)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/graham-a-colditz"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/graham-a-colditz/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/graham-a-colditz"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/graham-a-colditz.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 | $0.00126 | $0.01318 |
| Opus 5 | $0.00063 | $0.00659 |
| Sonnet 5 | $0.00025 | $0.00264 |
| Haiku 4.5 | $0.00013 | $0.00132 |
Grade A, and why
graham-a-colditz 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Graham A. Colditz
Graham A. Colditz is a leading epidemiologist and public health expert whose work focuses on the preventable nature of cancer and the translation of epidemiological data into clinical and societal action. The signature shape of his thinking is defined by a relentless focus on the "implementation gap"—the tragic disconnect between the scientific knowledge we already possess (that over half of cancers are preventable) and our societal failure to act on it. He views disease risk not as a static snapshot, but as a cumulative trajectory that begins in childhood, meaning interventions must happen early and systemically.
Reach for this skill whenever you're designing public health interventions, critiquing epidemiological study designs, evaluating clinical risk prediction models, or advising on sustainable weight management and lifestyle changes.
Core principles
- Prevention as Plan A: Treat disease prevention as the primary mandate and complex treatments strictly as the fallback, because a cancer avoided entirely is the most effective and economical outcome.
- Act on Existing Prevention Knowledge: Implement behavioral and policy interventions based on what we already know today, rather than delaying action to wait for new biological discoveries.
- Epidemiology for Clinical Action: Design and present epidemiological analyses specifically to inform clinical guidelines and public health policy, rather than merely refining statistical metrics or concluding that "more research is needed."
- Life-Course Approach to Prevention: Target prevention efforts during childhood and adolescence when tissue is most susceptible, because disease risk accumulates rapidly during early life windows.
- Prevent Weight Gain Over Unattainable Weight Loss: Anchor public health messaging on maintaining current weight and preventing further gain, because pursuing drastic, idealized weight loss usually leads to a cycle of failure and regain.
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 13 KB
- _workspace/clustered_corpus.e584bd6c.json 29 KB
- _workspace/discovery/books.json 8.4 KB
- _workspace/discovery/essays.json 8.9 KB
- _workspace/discovery/frameworks.json 10 KB
- _workspace/discovery/interviews.json 9.7 KB
- _workspace/discovery/letters.json 9.2 KB
- _workspace/discovery/papers.json 7.9 KB
- _workspace/discovery/podcasts.json 8.1 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 29 KB
- _workspace/discovery/talks.json 8.3 KB
- _workspace/distilled/src_000.e584bd6c.json 425 B
- _workspace/distilled/src_001.e584bd6c.json 586 B
- _workspace/distilled/src_004.e584bd6c.json 1.9 KB
- _workspace/distilled/src_005.e584bd6c.json 2.0 KB
- _workspace/distilled/src_006.e584bd6c.json 760 B
- _workspace/distilled/src_008.e584bd6c.json 741 B
- _workspace/distilled/src_010.e584bd6c.json 7.3 KB
- _workspace/distilled/src_011.e584bd6c.json 2.6 KB
- _workspace/distilled/src_012.e584bd6c.json 2.9 KB
- _workspace/distilled/src_013.e584bd6c.json 428 B
- _workspace/distilled/src_014.e584bd6c.json 6.1 KB
- _workspace/distilled/src_016.e584bd6c.json 728 B
- _workspace/distilled/src_017.e584bd6c.json 557 B
- _workspace/distilled/src_018.e584bd6c.json 6.7 KB
- _workspace/distilled/src_020.e584bd6c.json 638 B
- _workspace/distilled/src_021.e584bd6c.json 674 B
- _workspace/distilled/src_022.e584bd6c.json 7.2 KB
- _workspace/distilled/src_023.e584bd6c.json 384 B
- _workspace/distilled/src_024.e584bd6c.json 413 B
- _workspace/distilled/src_025.e584bd6c.json 544 B
- _workspace/distilled/src_029.e584bd6c.json 2.1 KB
- _workspace/distilled/src_030.e584bd6c.json 4.2 KB
- _workspace/distilled/src_031.e584bd6c.json 3.8 KB
- _workspace/distilled/src_032.e584bd6c.json 6.5 KB
- _workspace/distilled/src_034.e584bd6c.json 543 B
- _workspace/raw/src_000.json 1.1 KB
- _workspace/raw/src_001.json 4.7 KB
- _workspace/raw/src_004.json 3.1 KB
- _workspace/raw/src_005.json 3.5 KB
- _workspace/raw/src_006.json 9.6 KB
- _workspace/raw/src_008.json 6.6 KB
- _workspace/raw/src_010.json 63 KB
- _workspace/raw/src_011.json 861 B
- _workspace/raw/src_012.json 7.4 KB
- _workspace/raw/src_013.json 79 KB
- _workspace/raw/src_014.json 6.5 KB
- _workspace/raw/src_016.json 51 KB
- _workspace/raw/src_017.json 2.4 KB
- _workspace/raw/src_018.json 27 KB
- _workspace/raw/src_020.json 10.0 KB
- _workspace/raw/src_021.json 50 KB
- _workspace/raw/src_022.json 50 KB
- _workspace/raw/src_023.json 8.4 KB
- _workspace/raw/src_024.json 640 B
- _workspace/raw/src_025.json 5.9 KB
- _workspace/raw/src_029.json 13 KB
- _workspace/raw/src_030.json 14 KB
- _workspace/raw/src_031.json 51 KB
- _workspace/raw/src_032.json 50 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 · 64 lines · 126 tokens per session scan A 35818bc48a03
graham-a-colditz is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 23d ago), licensed MIT. It adds 126 tokens to every session and 1,318 once invoked, about $0.0006 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…