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/epicsagas/toefl-prep/agents-mdgit clone --depth 1 https://github.com/epicsagas/toefl-prepWrote 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/instructions/epicsagas/toefl-prep/agents-md)<a href="https://agentmods.dev/instructions/epicsagas/toefl-prep/agents-md"><img src="https://agentmods.dev/badge/instructions/epicsagas/toefl-prep/agents-md.svg" alt="Measured on agentmods" 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 | $0.01035 | $0.01035 |
| Opus 5 | $0.00517 | $0.00517 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade A, and why
toefl-prep AGENTS.md scanned grade A 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -L https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin \ How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — toefl-prep plugin
공유 에이전트 가이드. Claude Code·Codex·agy 세 호스트가 모두 이 파일을 시스템 프롬프트로 로드한다.
역할
TOEFL iBT 4주 집중 학습 플러그인. Reading/Listening/Speaking/Writing 4개 영역을 **로컬 모델(Ollama + whisper.cpp)**로 오프라인 평가한다. 워크플로·루브릭·채점 전략·한계 규칙은 skills/toefl/SKILL.md 가 권위적 문서다. 사용자가 토플 관련 요청("토플", "스피킹 연습", "라이팅 채점", "리딩 문제", "모의고사", "어떤 주차", "점수 확인" 등)을 하면 그 스킬을 따른다.
의존성 (사전 설치 필요)
이 플러그인은 외부 CLI에 의존한다. 자동 설치 훅이 없으므로 사용자가 사전에 설치해야 한다.
- Ollama (LLM 평가/문제 생성):
brew install ollama && ollama serve+ollama pull qwen2.5:7b-instruct(추천, M2 16GB 최적) 또는ollama pull llama3.1:8b(폴백). - whisper.cpp (스피킹 STT):
brew install whisper-cpp+ 모델 다운로드:mkdir -p ~/.local/share/whisper curl -L https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-base.en.bin \ -o ~/.local/share/whisper/ggml-base.en.bin - ffmpeg (오디오 정규화, 권장):
brew install ffmpeg - PyYAML (로드맵 계산):
pip3 install pyyaml—scripts/roadmap.sh가 schedule.yaml 파싱에 사용.
스크립트(scripts/config.sh)가 모델 자동 선택을 시도하지만, 미설치 시 사용자에게 설치 명령을 안내한다.
학습 일정 (사용자 커스텀)
날짜/요일/시간대/목표는 하드코딩되지 않는다. ${TOEFL_DATA_DIR}/schedule.yaml이 단일 진실 원천이며,
scripts/roadmap.sh가 현재 주차·D-day·오늘 스케줄을 계산한다. 템플릿은 skills/toefl/schedule.example.yaml.
schedule.yaml이 없으면 roadmap.sh가 복사 안내를 출력한다.
스크립트/루브릭 경로
- 평가 스크립트:
${CLAUDE_PLUGIN_ROOT}/scripts/아래.- Claude Code →
${CLAUDE_PLUGIN_ROOT} - Codex / agy → 각 호스트의 플러그인 루트 환경 변수로 치환. 변수를 모르면 스킬 디렉토리를 먼저 식별한 뒤 절대경로로 실행.
- Claude Code →
- 루브릭:
${CLAUDE_PLUGIN_ROOT}/rubrics/{reading,listening,speaking,writing}.md. - 데이터 저장: OS 문서 폴더 하위
~/Documents/toefl-prep/(macOS/Linux). 환경변수TOEFL_DATA_DIR로 오버라이드 (레거시TOEFL_VAULT_DIR호환). 공개 레포이므로 로컬 경로를 하드코딩하지 않는다. - schedule.yaml 자동 생성 금지:
roadmap.sh는 schedule.yaml이 없으면 사용자에게 대화형으로 묻고Y일 때만 템플릿을 복사한다. 자동으로 덮어쓰지 않는다.
호스트별 차이
- Claude Code:
commands/(5개 슬래시 명령) + SKILL 모두 사용. - Codex / agy:
commands/미지원 → SKILL.md의 "의도 → 액션 매핑" 표를 따라 동일한 워크플로를 스크립트 직접 호출로 수행.
윤리·정직성 (요약 — 전문은 SKILL.md)
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.
- 3d ago First seen · 51 lines · 1,035 tokens per session scan A 35230e8f4e37
toefl-prep AGENTS.md is an instructions file published in the GitHub repository epicsagas/toefl-prep (1 stars, last pushed yesterday), licensed MIT. It adds 1,035 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
ccplugin-opencode-bridge CLAUDE.md
Instructions for SkyWalker2506/ccplugin-opencode-bridge, covering ccplugin-opencode-bridge — yönlendirici, her oturum başında and değişiklik.
row-bot AGENTS.md
Instructions for siddsachar/row-bot, covering agents.md, project identity, ground rules, repository map and before editing.
row-bot CLAUDE.md
Instructions for siddsachar/row-bot, a project described as: Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge graph, voice, vision, shell, browser automation, scheduled tasks, health tracking, and messaging channels. Run locally via Ollama or add opt-in cloud…
pxx AGENTS.md
AGENTS.md instructions for cdnwetzel/pxx, covering agents.md — working agreements for ai agents in this repo, what this is, commands, hard rules and conventions.
mcp-local-llm AGENTS.md
Instructions for aplaceforallmystuff/mcp-local-llm, covering agents.md - mcp-local-llm, tech stack, architecture, development commands and environment variables.
hermit-agent CLAUDE.md
Instructions for cafitac/hermit-agent, covering hermit project — mcp executor, key modules, public cli, tests and product boundary.