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 instructions/pytorchkr/terms-kr/agents-mdgit clone --depth 1 https://github.com/PyTorchKR/terms-krWhat 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 | $0.01260 | $0.01260 |
| Opus 5 | $0.00630 | $0.00630 |
| Sonnet 5 | $0.00252 | $0.00252 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
terms-kr AGENTS.md 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 2d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to AI coding agents working in this repository.
Project Context
AI/ML 용어집 - 빠르게 변화하는 AI/ML 분야의 용어를 표준화하여 사람과 AI 번역 도구 모두가 일관된 한국어 번역을 사용할 수 있도록 하는 오픈소스 프로젝트. 파이토치 한국 사용자 모임(PyTorchKR) 운영. 현재 PoC 단계이며, 수록된 용어 데이터는 AI 생성 초안.
Repository: PyTorchKorea/kr-terms-poc (branch: poc)
Commands
npm install # Install dependencies
npm run dev # Dev server (http://localhost:5173), auto-copies data/ to public/data/
npm run build # TypeScript check + Vite production build
npm run lint # ESLint
npm run preview # Preview production build
No test framework is configured. Validation runs in CI via inline Node script in .github/workflows/deploy.yml.
Architecture
Static SPA for AI/ML Korean terminology glossary. No backend; all data is JSON fetched at runtime.
Stack: React 19 + TypeScript + Vite + MUI v7, deployed to GitHub Pages (poc.terms.kr).
Routing (App.tsx): HashRouter with lazy-loaded pages.
/->SearchPage(search + alphabet filter)/term/:termId->TermDetailPage(accordion per meaning, related terms)/about->AboutPage
Data flow: data/index.json lists alphabet JSON files (a.json..w.json). At build time, prebuild copies data/ -> public/data/. At runtime, loadTerms.ts fetches all files in parallel via Promise.all, flattens, and sorts. The useTerms hook caches this; useSearch debounces (200ms) and filters across term, korean, synonyms.
Homepage: SearchPage embeds HeroSection (stats) + AlphabetNavigation (A-Z chips) + TermCard grid. The Layout component wraps non-home pages with AppBar + footer; home page hides AppBar.
Data Model
Defined in src/types/term.ts:
interface TermExample { en: string; ko: string; source?: string }
interface TermMeaning {
korean: string // Required
definition: string // Required
examples: (string | TermExample)[] // Union type for backward compat
synonyms: string[]
}
interface Term {
term: string
meanings: TermMeaning[]
issueNumber?: number // GitHub Issue number for traceability
notes?: string // Editorial notes (why this translation was chosen)
}
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.
- 2d ago First seen · 109 lines · 1,260 tokens per session scan A f28e7a830899
terms-kr AGENTS.md is an instructions file published in the GitHub repository PyTorchKR/terms-kr (5 stars, last pushed 21d ago), licensed MIT. It adds 1,260 tokens to every session, about $0.0063 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 2026-08-31.
Other instructions, from other repositories
open-dictionary AGENTS.md
Instructions for ahpxex/open-dictionary, covering open dictionary rewrite charter, product framing, core workflow, technical framework and 1. raw ingestion layer.
designing-real-world-ai-agents-workshop CLAUDE.md
Instructions for iusztinpaul/designing-real-world-ai-agents-workshop, covering project, project structure, tech stack, access documentation and running qa.
ab900 CLAUDE.md
Instructions for timothywarner-org/ab900, covering claude.md, repository purpose, architecture, commands and 2. non-ascii punctuation -- must return zero.
canvas-lms-mcp AGENTS.md
Instructions for bruchris/canvas-lms-mcp, covering agents.md — canvas lms mcp server, quick start, run with npx (no install needed), or install globally and architecture.
obsidian-university-workflow CLAUDE.md
Instructions for ABO896/obsidian-university-workflow, covering obsidian university workflow, project structure, rules for working on this project, templater api — always read the docs first and config alignment.
paper-pilot CLAUDE.md
Instructions for aytzey/paper-pilot, covering claude.md, best fit, setup, first workflow to try and claude prompt patterns.