Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add epicsagas/toefl-prep/plugin install 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/skills/epicsagas/toefl-prep/toefl)<a href="https://agentmods.dev/skills/epicsagas/toefl-prep/toefl"><img src="https://agentmods.dev/badge/skills/epicsagas/toefl-prep/toefl.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 5.1 | $0.00149 | $0.02056 |
| Opus 5 | $0.00075 | $0.01028 |
| Sonnet 5 | $0.00030 | $0.00411 |
| Haiku 4.5 | $0.00015 | $0.00206 |
Grade A, and why
toefl 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.
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.
TOEFL 학습 도우미 (toefl-prep)
4주 집중 로드맵(7/15–8/12) + 로컬 LLM 기반 문제 생성/채점 + whisper.cpp 스피킹 평가. 모든 채점은 오프라인 로컬 모델로 수행한다.
스크립트/루브릭 위치: 평가 엔진은 플러그인 디렉토리 아래
${CLAUDE_PLUGIN_ROOT}/scripts/(Ollama 래퍼, whisper.cpp 래퍼, 환경설정) 와${CLAUDE_PLUGIN_ROOT}/rubrics/(4개 영역 루브릭) 에 있다. Claude Code는${CLAUDE_PLUGIN_ROOT}, Codex/agy는 각 호스트의 플러그인 루트 변수로 치환한다. 변수를 모르면 먼저 스킬 디렉토리를 식별한 뒤 절대경로로 실행한다.호스트별 워크플로: Claude Code는
commands/의 슬래시 명령(/toefl-roadmap등)을 직접 쓴다. Codex/agy는 아래 "의도 → 액션 매핑" 표를 따라 동일한 스크립트를 직접 호출한다 — 아래 각 영역별 명령 박스의 bash 블록이 호스트 중립적 진실 원천이다.
학습 일정 (사용자 커스텀)
날짜·요일·시간대·목표는 하드코딩되지 않는다. 모두 ${TOEFL_DATA_DIR}/schedule.yaml에서
사용자가 설정한다 (skills/toefl/schedule.example.yaml이 템플릿).
start_date/end_date/test_window_*/reporting_deadline— 타임라인study_days.weekdays/study_days.weekend— 학습 요일 (원하는 요일만 나열)hours.weekday/hours.weekend/*_window— 요일별 시간·선호 시간대target_score/purpose— 목표 점수·용도weeks: []— 주차별 focus + tasks (start_date 기준 자동 정렬)
현재 주차/D-day/오늘 스케줄은 scripts/roadmap.sh가 계산:
scripts/roadmap.sh all [YYYY-MM-DD] # 요약
scripts/roadmap.sh json # {week, dday_test, today_hours, target_score, current_week...}
의존성: PyYAML (pip3 install pyyaml). schedule.yaml이 없으면 roadmap.sh가 설치 안내를 출력한다.
예시 기본값(Georgia Tech OMSCS 2027 Spring)이 템플릿에 들어있으나, 사용자가 자유롭게 변경한다.
의도 → 액션 매핑
| 사용자 의도 | 명령/스크립트 |
|---|---|
| "오늘 뭐 해야 돼", "로드맵", "몇 주차야" | /toefl-roadmap |
| "리딩 문제 만들어줘", "스피킹 연습", "문제 풀고 싶어" | /toefl-practice [section] [count] |
| "이 답안 채점해줘", "라이팅 채점", "녹음 평가해줘" | /toefl-grade [section] [file] |
| "취약점 집중", "딥 드릴" | /toefl-drill [weakness] |
| "점수 현황", "진행도", "지금 몇 점이야" | /toefl-status |
4개 영역 평가 전략 (로컬 모델 라우팅)
각 영역은 특성에 맞춰 다른 평가 경로를 사용한다. 핵심 스크립트:
scripts/llm_eval.sh grade <prompt> <rubric>— Ollama 호출, JSON 점수 반환scripts/stt_transcribe.sh <audio>— whisper.cpp 전사 (스피킹 전용)scripts/config.sh— 모델 자동 선택 (qwen2.5:7b-instruct 우선, llama3.1:8b 폴백)
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 117 lines · 149 tokens per session scan A fa567e66a08f
toefl is a skill published in the GitHub repository epicsagas/toefl-prep (1 stars, last pushed 4d ago), licensed MIT. It adds 149 tokens to every session and 2,056 once invoked, about $0.0007 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 skills, from other repositories
ai-portable-setup
Erstellt einen portablen KI-Arbeitsbereich auf einem USB-Stick oder beliebigen Laufwerk. RAG-Pipeline mit lokalen LLM-Modellen (Ollama), Vektordatenbank (ChromaDB) und vorkonfigurierten Prompts.
opencode-bridge
Auto-trigger for OpenCode, Zen cloud models, Ollama local models, and free/open-source LLM requests. Routes to /opencode command.
textbook-distillation
Turn a textbook or long-form source into a self-paced learning track: chapter map, lesson plan, then self-contained HTML lecture notes (styled as the human specifies) with worked examples, exercises, and checkpoint questions. Read this for "lecture notes" / "study notes" / "course" / "syllabus" requests from a…
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
designer_guide
Guidance for creating and editing designs using the designer tool.
learning-and-development
Builds capability — skills gaps, career frameworks, training that transfers to the job, and internal mobility. Use this to design a career ladder, close a capability gap, decide whether to build or hire a skill, structure onboarding into a role, or work out why training keeps failing to change anything.