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/abilityai/cornelius/epistemic-classificationnpx skills add Abilityai/cornelius --skill epistemic-classificationgit clone --depth 1 https://github.com/Abilityai/corneliusWrote 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/abilityai/cornelius/epistemic-classification)<a href="https://agentmods.dev/skills/abilityai/cornelius/epistemic-classification"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/epistemic-classification.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00040 | $0.01370 |
| Opus 5 | $0.00020 | $0.00685 |
| Sonnet 5 | $0.00008 | $0.00274 |
| Haiku 4.5 | $0.00004 | $0.00137 |
Grade A, and why
epistemic-classification 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 5d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Epistemic Classification Framework
CRITICAL: When extracting insights from research or synthesizing across domains, you MUST clearly distinguish between:
Classification Levels
1. Confirmed Research Findings
Empirically validated, peer-reviewed, replicated
- Tag:
#research-findingor#empirical-evidence - Language: "Research shows...", "Studies confirm...", "Evidence demonstrates..."
- Requirement: Source citation with publication year and journal
2. Theoretical Frameworks
Established models with strong theoretical backing
- Tag:
#theoretical-frameworkor#established-theory - Language: "The framework proposes...", "Theory suggests...", "Model predicts..."
- Note: Level of acceptance in field
3. Working Hypotheses
Testable propositions not yet validated
- Tag:
#hypothesisor#testable-hypothesis - Language: "A possible mechanism...", "This suggests...", "One hypothesis..."
- Mark as: "HYPOTHESIS:" in note title or frontmatter
- Include: What would validate/falsify this hypothesis
4. Speculative Synthesis
Original connections or interpretations
- Tag:
#speculative-synthesisor#original-synthesis - Language: "This might explain...", "A potential connection...", "Speculatively..."
- State clearly: "This is synthesis/interpretation, not established fact"
- Confidence level: Low (20-40%), Medium (40-70%), High (70-90%)
5. Research Gaps
Identified missing connections in literature
- Tag:
#research-gapor#unexplored-connection - Language: "Research has not yet explored...", "Gap identified..."
- Note: Why this gap matters
Mandatory Labeling for Hypotheses
When creating notes containing hypotheses or speculative synthesis:
---
title: [Title] (HYPOTHESIS) or [Title]
type: hypothesis / speculative-synthesis / working-theory
status: untested / under-investigation / partially-supported
confidence: low / medium / high
tags: #hypothesis #topic
---
**STATUS: HYPOTHESIS - NOT CONFIRMED BY RESEARCH**
[Content of hypothesis]
## Testable Predictions
[What would validate this]
## Current Evidence
[Supporting indirect evidence]
## Research Needed
[What studies would test this]
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.
- 5d ago First seen · 141 lines · 40 tokens per session scan A 508aad175b57
epistemic-classification is a skill published in the GitHub repository Abilityai/cornelius (105 stars, last pushed 11d ago), licensed MIT. It adds 40 tokens to every session and 1,370 once invoked, about $0.0002 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.
best-practices
Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).