epistemic-classification

epistemic-classification is a skill for Claude Code from Nathan-Schwartz/dotfiles. It costs 45 tokens per session (78 once invoked), scanned B, original, no licence file.

A set of definitions for labelling information as verified, inferred, or guessed. It also describes when sources or citations are required.

In plain words
What is it for?
It is for classifying knowledge-management content and applying consistent evidence and citation rules.
Why use it?
It helps agents distinguish confirmed facts from conclusions and uncertainty instead of presenting all information with the same confidence.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Good fit It is for classifying knowledge-management content and applying consistent evidence and citation rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nathan-schwartz/dotfiles/epistemic-classification
Install

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.

Any agent
npx skills add Nathan-Schwartz/dotfiles --skill epistemic-classification
Clone the repo
git clone --depth 1 https://github.com/Nathan-Schwartz/dotfiles

Made for: Claude Code.

Wrote 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.

agentmods badge for epistemic-classification

README.md
[![agentmods](https://agentmods.dev/badge/skills/nathan-schwartz/dotfiles/epistemic-classification.svg)](https://agentmods.dev/skills/nathan-schwartz/dotfiles/epistemic-classification)
Your own site
<a href="https://agentmods.dev/skills/nathan-schwartz/dotfiles/epistemic-classification"><img src="https://agentmods.dev/badge/skills/nathan-schwartz/dotfiles/epistemic-classification.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 78 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00078
Opus 5 $0.00023 $0.00039
Sonnet 5 $0.00009 $0.00016
Haiku 4.5 $0.00005 $0.00008

Measured 8d ago against content hash 99eea0a031a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

epistemic-classification scanned grade B with 1 finding 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

!`cat ~/.claude/references/epistemic-reference.md`
claude/.claude/skills/epistemic-classification/SKILL.md · 11 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Changes

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.

  1. 8d ago First seen · 11 lines · 45 tokens per session scan B 99eea0a031a1

Subscribe to this mod's changes

epistemic-classification is a skill published in the GitHub repository Nathan-Schwartz/dotfiles (5 stars, last pushed 7d ago), with no licence file. It adds 45 tokens to every session and 78 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

save-memory

Export and distill the current conversation into a memory file. Use when the user asks to save, remember, or note the current session for future context.

aiya000/dotfiles · 34 tokens

apply-to-agents-md-git-root

Distill non-obvious, reusable information from the current session into {git-root}/AGENTS.md for future agents working in this repo, creating a minimal {git-root}/CLAUDE.md pointer if one is missing. Use when the user asks to save session learnings to AGENTS.md, or record project facts learned this session.

aiya000/dotfiles · 77 tokens

save-pipeline-memory

Capture a multi-step workflow into a timestamped pipeline memory after trial-and-error sessions. The core output is: (1) the final working commands saved as executable scripts (not bare shell commands), and (2) a structured markdown document separating the clean reproducible pipeline from the detours and pitfalls.…

magic3007/dotfiles · 154 tokens

apply-to-claude-md-home-root

Append general, cross-project information learned this session into the global /.claude/CLAUDE.md. Use when the user asks to save something globally, or when apply-to-agents-md-git-root identifies high-importance general information and the user confirms it should also go global.

aiya000/dotfiles · 66 tokens

session-search

Search previous Claude Code session history by keyword. Use when the user asks to find a past conversation, recall what was discussed, or locate a session where a topic came up.

DJRHails/dotfiles · 38 tokens

devlog

Keep DEVLOG.md up to date and use it to resume project context in the user's personal developer-log style. Use when the user asks to update, write, continue, summarize, resume, catch up from, or maintain @DEVLOG.md / DEVLOG.md after or before a work session, or asks to capture what they did, learned, decided, got…

wunki/dotfiles · 89 tokens