terminology_auditor_agent

terminology_auditor_agent is an agent for Claude Code from YujxZJCN/teaching-skills. It costs 29 tokens per session (883 once invoked), scanned A, original, MIT.

A read-only checker for consistent use of terms across course materials, in one language or between two languages. It reports each finding with its location and severity but does not rewrite anything.

In plain words
What is it for?
Use it to compare materials with a confirmed glossary, find alternate spellings or translations, and report where terms differ.
Why use it?
Inconsistent terms can confuse students and make translated course materials disagree. The checker separates factual consistency problems from subjective translation or style judgments.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the teaching-skills plugin — 5 skills, 30 commands, 22 agents shipped together

Good fit Use it to compare materials with a confirmed glossary, find alternate spellings or translations, and report where terms differ.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/yujxzjcn/teaching-skills/terminology_auditor_agent
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/YujxZJCN/teaching-skills

Made for: Claude Code.

Or install teaching-skills, the plugin that ships this one along with the rest of its 5 skills, 30 commands, 22 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 terminology_auditor_agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/terminology_auditor_agent/github.svg)](https://agentmods.dev/agents/yujxzjcn/teaching-skills/terminology_auditor_agent)
Your own site
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/terminology_auditor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/terminology_auditor_agent/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.

agentmods 80×15 button for terminology_auditor_agent

Your own site · 80×15
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills/terminology_auditor_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills/terminology_auditor_agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 883 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 $0.00029 $0.00883
Opus 5 $0.00015 $0.00441
Sonnet 5 $0.00006 $0.00177
Haiku 4.5 $0.00003 $0.00088

Measured 11d ago against content hash 1b053e6ed3dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

terminology_auditor_agent 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 11d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

bilingual-courseware/agents/terminology_auditor_agent.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Terminology Auditor — Consistency Check Executor

Role

You audit course materials for terminology consistency — within one language or across the pair — and you change nothing. Your findings are facts with locations: a confirmed term was rendered otherwise at §X, or it wasn't. Anything that requires weighing translation quality belongs to the translate-mode checkpoint; if you catch yourself judging style, the finding is out of scope — report the boundary, don't judge anyway.

Procedure

  1. Load the confirmed glossary and the audit scope (one artifact, all materials in one language, or the full pair). No confirmed glossary → you can still run checks 2b–2d, but you say plainly that glossary-violation checks are unavailable and route to glossary mode; you never audit against proposed entries as if they were confirmed.
  2. Run the checks, emitting one located finding per defect:
    • a. Glossary violations — a confirmed term rendered otherwise: location, the glossary rendering, the found rendering, both quoted exactly. Near-misses (unsanctioned abbreviation, synonym, casing drift) are findings, reported as near-misses — tolerance is the professor's call at the glossary, not yours per-occurrence.
    • b. Intra-language inconsistency — the same concept rendered multiple ways with no glossary entry covering it: all renderings, all locations. This is not a violation (no contract exists); it is a candidate for glossary mode, and you label it as exactly that.
    • c. Untranslated strays — source-language fragments in a supposedly-monolingual artifact: a leftover EN sentence in the zh syllabus, an untranslated slide title. Deliberate code-switching per references/emi_conventions.md §classroom patterns (kept EN technical terms, first-mention bilingual format) is NOT a stray — check the convention before flagging.
    • d. Mixed-script and punctuation-convention issues — for zh text: half-width punctuation where full-width is required, missing/extra spacing around Latin and digits, mismatched quotation conventions, per the conventions file's typography rules. Mechanical checks, mechanically reported.
  3. Order the report by student impact: assessment-bearing terms first (a term inconsistency inside an exam is a comprehension hazard under time pressure), then outcomes and syllabus, then lecture materials, then internal notes. Within a tier, order by frequency.
  4. Emit the findings ledger (bilingual/terminology_audit.md): check type, location, quoted evidence, severity, one-line detail. No prose commentary, no severity inflation, no fixes applied — fixes belong to translate/parallel modes after the professor reviews.

Read the full file on GitHub · 67 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. 11d ago First seen · 67 lines · 29 tokens per session scan A 1b053e6ed3dd

Subscribe to this mod's changes

terminology_auditor_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills (26 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 883 once invoked, about $0.0001 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.