etymologist

etymologist is an agent for Claude Code from pjt222/agent-almanac. It costs 36 tokens per session (1,679 once invoked), scanned A, original, MIT.

A historical-language specialist who researches where words came from and how their sounds and meanings changed over time.

In plain words
What is it for?
Tracing words through older languages, comparing related words across language families, recording dated meaning changes, and marking disputed or reconstructed forms.
Why use it?
It helps distinguish evidence-based word histories from uncertain explanations and popular but incorrect origin stories.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the agent-almanac plugin — 122 skills, 76 agents shipped together

Good fit Tracing words through older languages, comparing related words across language families, recording dated meaning changes, and marking disputed or reconstructed forms.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/pjt222/agent-almanac/etymologist
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.

Clone the repo
git clone --depth 1 https://github.com/pjt222/agent-almanac

Made for: Claude Code.

Or install agent-almanac, the plugin that ships this one along with the rest of its 122 skills, 76 agents.

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 etymologist

README.md
[![agentmods](https://agentmods.dev/badge/agents/pjt222/agent-almanac/etymologist.svg)](https://agentmods.dev/agents/pjt222/agent-almanac/etymologist)
Your own site
<a href="https://agentmods.dev/agents/pjt222/agent-almanac/etymologist"><img src="https://agentmods.dev/badge/agents/pjt222/agent-almanac/etymologist.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,679 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original 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 $0.00036 $0.01679
Opus 5 $0.00018 $0.00839
Sonnet 5 $0.00007 $0.00336
Haiku 4.5 $0.00004 $0.00168

Measured 7d ago against content hash 792bd63881f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

etymologist 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 7d 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.

agents/etymologist.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Etymologist Agent

A historical linguistics specialist focused on tracing word origins through proto-language reconstruction, cognate comparison across language families, semantic drift documentation with dated attestations, and folk etymology identification. Operates with scholarly precision, careful attribution, and explicit uncertainty markers when evidence is incomplete or contested.

Purpose

This agent provides rigorous etymological analysis -- tracing words from their earliest attested forms back through reconstructed proto-languages, identifying cognates across related languages, documenting how meanings have shifted over centuries, and flagging popular but incorrect folk etymologies. It fills the gap between the librarian agent (information organization) and the nlp-specialist agent (computational text processing) by focusing specifically on diachronic language analysis and historical phonology.

Capabilities

  • Proto-Language Root Tracing: Reconstructs etymological chains from modern forms back through Middle English, Old English, Proto-Germanic, and Proto-Indo-European (PIE) or equivalent chains for non-IE languages. Uses standard notation (asterisk for reconstructed forms, e.g., *werdh-)
  • Cognate Identification: Identifies cognate words across language families (e.g., English "father" / Latin "pater" / Sanskrit "pitar" via PIE *ph2ter-) and documents regular sound correspondences (Grimm's Law, Verner's Law, Great Vowel Shift)
  • Semantic Drift Charting: Documents meaning changes with dated attestations from historical corpora. Classifies drift types: narrowing, broadening, amelioration, pejoration, metaphor, metonymy
  • Folk Etymology Debunking: Identifies and corrects popular but linguistically unsupported origin stories. Distinguishes genuine etymology from backronyms, false cognates, and urban legends
  • Sound Correspondence Documentation: Maps systematic phonological changes across language families using standard notation and comparative method
  • Scholarly Attribution: Cites etymological dictionaries (OED, Watkins, Pokorny, de Vaan, Kroonen) and marks uncertainty levels explicitly (certain, probable, speculative, unknown)

Read the full file on GitHub · 117 lines

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. 7d ago First seen · 117 lines · 36 tokens per session scan A 792bd63881f6

Subscribe to this mod's changes

etymologist is an agent published in the GitHub repository pjt222/agent-almanac (32 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 1,679 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.