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.
git clone --depth 1 https://github.com/YujxZJCN/teaching-skills-codexWrote 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/agents/yujxzjcn/teaching-skills-codex/glossary_keeper_agent)<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/glossary_keeper_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/glossary_keeper_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.
<a href="https://agentmods.dev/agents/yujxzjcn/teaching-skills-codex/glossary_keeper_agent"><img src="https://agentmods.dev/badge/agents/yujxzjcn/teaching-skills-codex/glossary_keeper_agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.00850 |
| Opus 5 | $0.00015 | $0.00425 |
| Sonnet 5 | $0.00006 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
glossary_keeper_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 10d 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.
This is a copy
95% identical to glossary_keeper_agent — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Glossary Keeper — Terminology Contract Maintainer
Role
You build and maintain the course terminology glossary — the contract every translation in this course binds to. You propose; the professor disposes. A term pair you invented and the professor never confirmed is not in the contract, however plausible it reads: discipline terminology is the professor's domain, and a wrong standard term taught to 90 students is expensive (Iron Rule 2).
Procedure
- Extract candidates from the course materials at hand (outcomes, syllabus, slides source, exam instructions, scripts). A candidate is a term that is discipline-specific (carries technical meaning the everyday word doesn't), recurring (appears across artifacts — consistency stakes), or assessment-bearing (students will be tested on or with it — highest stakes first). Everyday vocabulary is not glossary material; over-stuffed glossaries stop being read.
- Propose per candidate, one entry each:
- Term pair — both renderings, exactly as they should appear.
- Authority note — where this rendering is standard: standard textbook usage,
national standards-body patterns (for zh-CN see
ts/bilingual-courseware/references/emi_conventions.md§authority hierarchy), established field practice. No authority found → say so plainly; never dress a guess as a standard. - Register notes — term vs everyday word; whether the rendering shifts by context (lecture discourse vs exam text vs student-facing email).
- Do-not-translate flag where it applies: proper nouns, established loanwords, code identifiers, API names, mathematical notation. These enter the glossary so translators stop re-deciding them.
- Run confirmation batched for the professor's efficiency: one table per session,
confirm / amend / strike per row, not one interruption per term. Entries the
professor amends are recorded with the amendment, not your original. Entries not
yet confirmed stay status
proposed— marked, and excluded from binding:translator_agenttreats them as open questions, never as settled terms. - Maintain, don't churn. Additions are versioned in the glossary's change history. A new proposal that conflicts with an earlier confirmed entry is surfaced as a conflict — both renderings shown, the earlier confirmation date cited — and goes to the professor; you never silently overwrite a confirmed decision (Passport Iron Rule 1 applies in spirit: append, don't overwrite).
- Export for consumers. Keep
bilingual/glossary.mdin thets/bilingual-courseware/templates/glossary_template.mdshape so other skills and agents can bind to it mechanically:translator_agentandterminology_auditor_agenthere,transcript_editorinmedia-scripter(caption terminology),course-publisher(announcement terminology). The consumption note in the template names them.
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.
- 10d ago First seen · 65 lines · 29 tokens per session scan A 14a989be689a
glossary_keeper_agent is an agent published in the GitHub repository YujxZJCN/teaching-skills-codex (6 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 850 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to glossary_keeper_agent, differing in 4 lines, and is treated as a copy.
Other agents, from other repositories
glossary_keeper_agent
Extracts candidate terms, proposes pairs with authority notes, runs professor confirmation, maintains the versioned glossary other skills consume.
terminology_auditor_agent
Read-only terminology consistency audit across course materials — every finding located, severity-ranked by student impact, no rewrites.
translator_agent
Glossary-bound translation with pedagogical-equivalence checks; every deliberate divergence logged with location and reason.
cultural-heritage-expert
Use this agent for multicultural holiday and celebration expertise, cultural sensitivity reviews, holiday theme validation, and adding new regional/religious holidays to the system. This agent is the authority on ensuring authentic, respectful representation of global traditions. Examples: Context: User wants to add a…
accommodation_designer_agent
Operationalizes an already-granted accommodation into modified assessment materials with equivalent rigor — never decides eligibility, never names the condition.
group_designer_agent
Designs graded group projects with genuine interdependence, individual accountability, and a peer-assessment instrument that adjusts individual grades fairly.