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 skills/lingochunk/mcp/lingochunk-overviewnpx skills add lingochunk/mcp --skill lingochunk-overviewgit clone --depth 1 https://github.com/lingochunk/mcpWrote 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/lingochunk/mcp/lingochunk-overview)<a href="https://agentmods.dev/skills/lingochunk/mcp/lingochunk-overview"><img src="https://agentmods.dev/badge/skills/lingochunk/mcp/lingochunk-overview.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 | $0.00073 | $0.01203 |
| Opus 5 | $0.00036 | $0.00602 |
| Sonnet 5 | $0.00015 | $0.00241 |
| Haiku 4.5 | $0.00007 | $0.00120 |
Grade A, and why
lingochunk-overview 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 4d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What you can do with LingoChunk
You are connected to the user's LingoChunk account: their episodes with timestamped transcripts and native audio, their FSRS-graded vocabulary, their decks and lessons, and (for creators) the collections they publish. This guide is the menu of what to offer.
How to answer "what can I do?"
- Answer short first: one line per area below, each with its example prompt. Do NOT dump this whole guide on the user.
- Then ask which area to go deeper on - or just do the thing they pick.
- Before actually composing anything, call
get_authoring_guidewith the area's topic (in parentheses below) and follow it; that is where the craft rules live. Areas marked "no guide" need no preparation. - If a tool answers 403 naming a scope, the connection was granted narrow permissions: tell the user to reconnect (or mint a token with that scope) via LingoChunk -> Settings -> API tokens.
The menu
For every learner:
- Talk through an episode (topic
discuss) - work through a real episode conversationally, explaining grammar and vocabulary as they come up, grounded in the user's own data. Example: "Talk me through yesterday's episode and explain the tricky bits." - Check words and quiz (no guide) - the user's vocabulary with live maturity states: known, learning, new, due. Example: "Which of my German words are due today? Quiz me on them."
- Build a lesson (topic
lesson) - a coursebook-style lesson the app renders natively: real-audio exercises, gap-fills, dictation, shadowing, one grammar point, an AI tutor, an offline worksheet download. Example: "Build a B1 lesson from the first five minutes of episode 12." - Revise a lesson (topic
lesson) - edit a saved lesson IN PLACE (same id and links): the app's Co-edit mode labels each block §1, §2, ... and refreshes live, so the user points at a block and watches your edit land within seconds. Example: "In my lesson, change §5 to a two-person dialogue." - Build a course (topic
course) - a named, ordered series of lessons with a different grammar point per lesson and ramping difficulty. Example: "Turn this 20-minute episode into a four-lesson course, A2 to B1." - Build a guided study path (topic
guided) - the app segments an episode into ordered study sections and you write each part following the server's runtime brief; the parts render natively like internally generated ones, feeding the guided page and remembered progress. Planning is server-side; the writing runs on this agent. Example: "Build a guided path over episode 12 and write the lessons." - Make flashcards and export to Anki (topic
cards) - native-grade cards anchored to verbatim sentences (highlight/blur painting, native audio clip), plus.apkgdeck export. Example: "Make cards for the idioms in episode 12, then export the deck to Anki." - Add languages (topic
add-language) - fan an episode out into up to ten more languages server-side, or hand-craft the translation sentence by sentence - including simplified same-language versions (e.g. German audio glossed in easier A2 German). Example: "Add Polish and Turkish to episode 12." or "Make a simplified German (A2) version of it."
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.
- 4d ago First seen · 92 lines · 73 tokens per session scan A 3b6aa013577d
lingochunk-overview is a skill published in the GitHub repository lingochunk/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 1,203 once invoked, about $0.0004 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
anki
Use when the user wants to create Anki flashcards, manage Anki decks, search notes, or interact with Anki via AnkiConnect. Triggers on phrases like "create flashcards", "add to Anki", "make Anki cards", "batch create notes", or "manage my Anki deck".
vozclara-pack-from-url
Turn a YouTube URL into a structured Knowledge Pack via VozClara — summary, key ideas, glossary, vocabulary, citations, in the user's language. No sign-up needed for one-off use.
context7-docs
Fetch up-to-date documentation and code examples for any library, framework, SDK, CLI tool, or cloud service. Use whenever the user asks about a specific library — even well-known ones like React, Next.js, Prisma, Express, Tailwind, Django, or Spring Boot — because training data may not reflect recent API changes or…
learning-notes-automation
学习笔记自动化：视频/播客转录 → 知识点提取 → 闪卡生成 → 知识图谱更新。触发词：学习笔记、闪卡、Anki、知识提取、视频学习.
frontmcp-guides
Tutorials, end-to-end walkthroughs, and complete reference projects for FrontMCP. Use when you want a getting-started guide, a full worked example, or to learn best practices by following a step-by-step build rather than a single API reference. Includes a beginner weather-API server (tool plus static resource, Zod…
create-skill
Create instruction-only skills that package knowledge and workflow guides for AI clients.