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 thomas-edisongit 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/thomas-edison)<a href="https://agentmods.dev/skills/k-dense-ai/mimeographs/thomas-edison"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/thomas-edison/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/thomas-edison"><img src="https://agentmods.dev/badge/skills/k-dense-ai/mimeographs/thomas-edison.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 | $0.00103 | $0.01205 |
| Opus 5 | $0.00051 | $0.00602 |
| Sonnet 5 | $0.00021 | $0.00241 |
| Haiku 4.5 | $0.00010 | $0.00120 |
Grade A, and why
thomas-edison 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thinking like Thomas Edison
Thomas Edison was not just an inventor; he was a pioneer of industrial research and systems engineering. His signature cognitive move is shifting focus from the isolated, theoretical breakthrough to the complete, commercially viable ecosystem. He views innovation not as a flash of divine inspiration, but as a grueling, systematic process of elimination where practical utility and economic reality dictate the direction of research.
Edison's reasoning is deeply pragmatic. He dismisses "pure science" when it lacks a path to market, and he views failure not as a setback, but as a data point proving what doesn't work. He understands that a product cannot survive without its supporting infrastructure, and that true opportunity is usually disguised as tedious, unglamorous labor.
Reach for this skill whenever you're helping a user commercialize a product, design a complex system, evaluate whether to patent an idea, or push through a demoralizing series of iterative failures.
Core principles
- Failure is a Process of Elimination: Treat every unsuccessful attempt not as a defeat, but as a necessary step that eliminates a wrong path and brings you closer to the correct solution.
- Innovate Entire Systems, Not Just Components: Never design a product in isolation; simultaneously develop the complete, integrated infrastructure required to support, distribute, and monetize it.
- Inventions Must Be Practical and Profitable: Filter all technical pursuits by their ability to generate commercial demand and sustain themselves economically, because unscalable ideas cannot benefit society.
- Prove Ideas Before Patenting: Reduce an idea to actual practice and ensure it works before applying for a patent, because protecting an unproven concept is a waste of resources.
- Success Requires Continuous Hard Work: Recognize that high-value opportunities rarely present themselves as easy wins; they demand relentless effort and a willingness to engage in tedious labor.
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 8.9 KB
- _workspace/clustered_corpus.e584bd6c.json 17 KB
- _workspace/discovery/books.json 11 KB
- _workspace/discovery/essays.json 12 KB
- _workspace/discovery/frameworks.json 11 KB
- _workspace/discovery/interviews.json 10 KB
- _workspace/discovery/letters.json 8.1 KB
- _workspace/discovery/papers.json 9.8 KB
- _workspace/discovery/podcasts.json 8.0 KB
- _workspace/discovery/ranked_sources.e584bd6c.json 33 KB
- _workspace/discovery/talks.json 8.0 KB
- _workspace/distilled/src_002.e584bd6c.json 3.7 KB
- _workspace/distilled/src_003.e584bd6c.json 1.9 KB
- _workspace/distilled/src_004.e584bd6c.json 574 B
- _workspace/distilled/src_005.e584bd6c.json 535 B
- _workspace/distilled/src_007.e584bd6c.json 519 B
- _workspace/distilled/src_011.e584bd6c.json 573 B
- _workspace/distilled/src_014.e584bd6c.json 2.8 KB
- _workspace/distilled/src_015.e584bd6c.json 1.5 KB
- _workspace/distilled/src_016.e584bd6c.json 4.4 KB
- _workspace/distilled/src_017.e584bd6c.json 364 B
- _workspace/distilled/src_019.e584bd6c.json 1.8 KB
- _workspace/distilled/src_020.e584bd6c.json 658 B
- _workspace/distilled/src_026.e584bd6c.json 5.6 KB
- _workspace/distilled/src_029.e584bd6c.json 359 B
- _workspace/distilled/src_030.e584bd6c.json 405 B
- _workspace/distilled/src_033.e584bd6c.json 449 B
- _workspace/distilled/src_044.e584bd6c.json 2.3 KB
- _workspace/distilled/src_048.e584bd6c.json 3.7 KB
- _workspace/distilled/src_050.e584bd6c.json 498 B
- _workspace/distilled/src_052.e584bd6c.json 496 B
- _workspace/distilled/src_056.e584bd6c.json 405 B
- _workspace/distilled/src_058.e584bd6c.json 428 B
- _workspace/distilled/src_059.e584bd6c.json 497 B
- _workspace/distilled/src_060.e584bd6c.json 366 B
- _workspace/distilled/src_061.e584bd6c.json 313 B
- _workspace/raw/src_002.json 7.8 KB
- _workspace/raw/src_003.json 4.2 KB
- _workspace/raw/src_004.json 1.6 KB
- _workspace/raw/src_005.json 4.3 KB
- _workspace/raw/src_007.json 5.7 KB
- _workspace/raw/src_011.json 20 KB
- _workspace/raw/src_014.json 1.5 KB
- _workspace/raw/src_015.json 22 KB
- _workspace/raw/src_016.json 4.7 KB
- _workspace/raw/src_017.json 368 B
- _workspace/raw/src_019.json 789 B
- _workspace/raw/src_020.json 2.7 KB
- _workspace/raw/src_026.json 34 KB
- _workspace/raw/src_029.json 2.6 KB
- _workspace/raw/src_030.json 2.6 KB
- _workspace/raw/src_033.json 1.8 KB
- _workspace/raw/src_044.json 8.4 KB
- _workspace/raw/src_048.json 36 KB
- _workspace/raw/src_050.json 3.6 KB
- _workspace/raw/src_052.json 8.6 KB
- _workspace/raw/src_056.json 5.7 KB
- _workspace/raw/src_058.json 4.0 KB
- _workspace/raw/src_059.json 7.2 KB
- _workspace/raw/src_060.json 343 B
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.
- 9d ago First seen · 61 lines · 103 tokens per session scan A 7e95a74c6228
thomas-edison is a skill published in the GitHub repository K-Dense-AI/mimeographs (123 stars, last pushed 24d ago), licensed MIT. It adds 103 tokens to every session and 1,205 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 2026-09-03.
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…