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 skills add JayRHa/AgentSkills --skill language-tutorgit clone --depth 1 https://github.com/JayRHa/AgentSkillsWrote 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/jayrha/agentskills/language-tutor)<a href="https://agentmods.dev/skills/jayrha/agentskills/language-tutor"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/language-tutor/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/skills/jayrha/agentskills/language-tutor"><img src="https://agentmods.dev/badge/skills/jayrha/agentskills/language-tutor.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 | $0.00098 | $0.01099 |
| Opus 5.5 | $0.00039 | $0.00440 |
| Sonnet 5.5 | $0.00020 | $0.00220 |
| Haiku 4.5 | $0.00010 | $0.00110 |
Grade A, and why
language-tutor 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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Language Tutor
Overview
This skill is an adaptive language tutor. It assesses the learner's level, runs comprehensible-input conversation practice at the right difficulty, teaches vocabulary and grammar in context, corrects errors without killing momentum, and builds a spaced-repetition plan toward the learner's real goal (travel, conversation, exam, work).
Keywords: language learning, language tutor, conversation practice, Spanish, French, German, Italian, vocabulary, grammar, CEFR, spaced repetition, pronunciation, fluency, phrases for travel.
When to use vs. not
Use this for learning or practicing a language: conversation, grammar, vocabulary, writing correction, exam prep, or trip phrasebooks. Set expectations honestly — fluency takes sustained practice; this accelerates it, it doesn't replace it. For certified translation or legal/medical document accuracy, recommend a professional.
Inputs to gather first
- Target language and the learner's native/strong language (for explanations).
- Current level (none / beginner / intermediate / advanced, or CEFR A1–C2) — or assess it.
- Goal + deadline (travel in 8 weeks, B2 exam, hold a work conversation).
- Time available per week and preferred focus (speaking, reading, writing, listening).
- Interests — practice content is far stickier when it's about things they care about.
Workflow
- Assess the level. A few graded questions or a short free-write/conversation. Map roughly to CEFR (A1–C2). See
references/cefr-levels.md. Tailor everything to one notch above current ability (comprehensible input:i+1). - Set the goal + plan. Convert the goal into a weekly plan: speaking, vocab (spaced repetition), grammar-in-context, and listening/reading. See
references/study-plan.md. - Run practice in the target language at the right level, with scaffolding: use the target language primarily, drop to the native language for explanations when needed, and gloss new words inline the first time.
- Teach in context, not lists. Introduce vocab and grammar through sentences and short dialogues about the learner's interests; explain the pattern after showing it in use.
- Correct with the right touch. Don't interrupt the flow for every slip. Use recasts (model the correct form), batch minor corrections at the end of a turn, and explain only the patterns worth learning now. Prioritize errors that block meaning. See
references/correction-techniques.md. - Build retention. Pull new words/phrases into a spaced-repetition list; recycle them in later practice. Use the learner's own mistakes as the next lesson's material.
- Track progress + adjust. Note recurring errors and mastered structures; raise difficulty as comprehension improves; celebrate concrete milestones ("you just held a 5-minute conversation").
What ships with it
3 files 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.
- 1mo ago First seen · 60 lines · 98 tokens per session scan A 88480bb660eb
language-tutor is a skill published in the GitHub repository JayRHa/AgentSkills (12 stars, last pushed 2mo ago), licensed MIT. It adds 98 tokens to every session and 1,099 once invoked, about $0.0004 per session on Opus 5.5. 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
code-explainer
Paste any code snippet and get a plain English explanation of what it does and how it works.
semantic-kernel-guide
Développement d'agents IA avec Microsoft Semantic Kernel en .NET/C# et Python. Plugins natifs, plugins prompts, planners, filters, AgentGroupChat et intégration enterprise Azure. Se déclenche avec "Semantic Kernel", "SK", "Microsoft Semantic Kernel", "kernel plugin", "planner", "agent .NET", "C# agent", "enterprise…
fundamentals
Core programming concepts: variables, functions, conditionals, loops, and data types. Activated when Claude writes basic code structures. Provides teaching context for CodeSensei explanations at the foundational level.
pronunciation-and-usage
Explains how to pronounce and naturally use a selected word or phrase, with register, meaning, collocations, and example sentences. Use when the user asks "how do you pronounce / how do you say this", "what does X mean", or wants vocabulary and usage help for a foreign-language word or phrase.
spring-boot-engineer
Use when building Spring Boot 3.x applications, microservices, or reactive Java applications. Invoke for Spring Data JPA, Spring Security 6, WebFlux, Spring Cloud integration.
cli-developer
Use when building CLI tools, implementing argument parsing, or adding interactive prompts. Invoke for CLI design, argument parsing, interactive prompts, progress indicators, shell completions.