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 agentmods add skills/askarzh/epistemator/cartesiannpx skills add askarzh/epistemator --skill cartesiangit clone --depth 1 https://github.com/askarzh/epistematorWhat 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 | $0.00070 | $0.01648 |
| Opus 5 | $0.00035 | $0.00824 |
| Sonnet 5 | $0.00014 | $0.00330 |
| Haiku 4.5 | $0.00007 | $0.00165 |
Grade A, and why
cartesian 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 2d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cartesian Reductionist Analysis
Overview
A modern adaptation of Descartes' method of analysis from the Discourse on Method and Rules for the Direction of the Mind. This method systematically questions assumptions, decomposes, orders, and enumerates to arrive at clear and distinct understanding of any subject.
Unlike naive reductionism ("just break it into parts"), this method recognizes that decomposition can destroy emergent properties — wholes that behave differently from the sum of their parts. The reconstruction step is therefore essential: after decomposition, the analysis must account for how parts interact to produce the whole, including properties that exist only at the level of the whole.
Cartesian Reductionism excels at analyzing complex systems, unclear problems, tangled arguments, and any input where the whole is too complex to grasp without decomposition.
Core Methodology — The Four Rules
-
Rule of Evidence (Question Assumptions) — Accept nothing as true that is not clearly and distinctly known to be so. Identify every assumption, presupposition, and received opinion in the input. In applied analysis, this means testing assumptions against evidence and logic — not Descartes' radical hyperbolic doubt, but a practical inventory of what is well-grounded vs. what is merely taken for granted.
-
Rule of Division (Decompose) — Divide the subject into as many parts as possible and as necessary for adequate resolution. Each part should be simple enough to be understood in isolation. Continue subdividing until reaching elements that are self-evident or irreducible.
-
Rule of Order (Reconstruct) — Begin with the simplest, most easily known elements and ascend step by step to knowledge of the most complex. Each step must follow necessarily from the previous. Build understanding from foundations upward.
-
Rule of Enumeration (Verify) — Make enumerations so complete and reviews so comprehensive that nothing is omitted. Check every link in the chain. Ensure no part has been skipped or assumed.
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.
- 2d ago First seen · 124 lines · 70 tokens per session scan A 2cfacb7c7229
cartesian is a skill published in the GitHub repository askarzh/epistemator (3 stars, last pushed 6mo ago), licensed MIT. It adds 70 tokens to every session and 1,648 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
etsy-category-listing
Etsy category page scraper: given an Etsy category URL (e.g. https://www.etsy.com/c/jewelry) and optional page number, returns paginated product listings with listingId, shopId, title, url, image, salePrice, originalPrice, currency, rating, reviewCount, shopName, isAd, freeShipping, badge from category and subcategory…
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
research-report
Summarize deep research results into markdown report, cover all fields, skip uncertain values.
ddia-systems
Design data systems by understanding storage engines, replication, partitioning, transactions, and consistency models. Use when the user mentions "database choice", "which database should I use", "SQL or NoSQL", "replication lag", "partitioning strategy", "consistency vs availability", "stream processing", "ACID…
improve-website
Guided journey from a live website that underperforms to a prioritized, evidence-backed backlog of conversion, usability, message, and speed fixes - each shipped as a testable experiment. Orchestrates eight skills phase by phase - cro-methodology, ux-heuristics, refactoring-ui, web-typography, storybrand-messaging…