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-cardsnpx skills add lingochunk/mcp --skill lingochunk-cardsgit 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-cards)<a href="https://agentmods.dev/skills/lingochunk/mcp/lingochunk-cards"><img src="https://agentmods.dev/badge/skills/lingochunk/mcp/lingochunk-cards.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 | $0.00114 | $0.01278 |
| Opus 5 | $0.00057 | $0.00639 |
| Sonnet 5 | $0.00023 | $0.00256 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
lingochunk-cards 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 5d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LingoChunk card builder
Create cards that look exactly like the app's own: real sentence, target highlighted or blurred, native speaker audio, forward+reverse pairs. The division of labour: you choose what to teach and write the glosses; LingoChunk verifies the anchors and derives everything visual/audible.
This skill uses the lingochunk MCP tools. If they are not available, tell
the user to add the LingoChunk MCP server (see the plugin README) and stop.
The one rule that matters
Every span you send must be copied VERBATIM from the transcript. Fetch
the sentence with get_transcript first; focus_span must be the exact
surface form as spoken ("habe", not "haben"; "einem", not "ein"). The server
rejects non-verbatim spans on answer-hiding kinds
(code=focus_span_not_verbatim) because a paraphrased example breaks both
the blur painting and the audio alignment. Never invent or "improve" an
example sentence; if the episode has no good sentence for an item, skip the
item and say so.
Workflow
get_transcriptfor the episode (slice by time range if the user named one). Note each sentence'sposition- that is your anchor.- Pick targets. One card = one thing to learn. Prefer items the sentence demonstrates naturally.
add_cardper item with a card.v1 kind (below). Includenote(one-line why),hint(only when the answer has competing valid fills),cefrwhen you are confident.- Read the response.
problems[]lists degradations (focus_span_no_timings,context_position_unknown, ...). Fix what you can and resend - the same headword updates in place (created: false), so a correction never duplicates a card. - Report to the user what was added, kind by kind, and anything skipped.
Choosing a kind
| Kind | Use for | Front shows |
|---|---|---|
word |
one new word (include the article: "die Landschaft") | headword hero + example with the word highlighted |
phrase / idiom / collocation |
multi-word units, fixed combinations | same, multi-word headword |
chunk |
a whole useful sentence/utterance | the chunk as headword |
grammar |
a form choice the sentence demonstrates (case ending, article, verb form, word order) | example with the morpheme blurred + "why" slot |
cloze |
recall one content word in context | example with the word blurred |
contrast |
2-3 confusables (wissen/kennen) | option chips + gap in the example |
qa |
an explanation with no single gap | the question as prose |
production |
meaning → produce the target phrase | the gloss as prompt, target blurred |
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.
- 5d ago First seen · 97 lines · 114 tokens per session scan A 8edaa17a10f6
lingochunk-cards is a skill published in the GitHub repository lingochunk/mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 114 tokens to every session and 1,278 once invoked, about $0.0006 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.
notebooklm
This skill should be used when the user wants to query their Google NotebookLM notebooks for citation-backed, source-grounded answers, or manage notebooks, sources, and Studio content (audio, report, video, infographic, presentation, data table, flashcards, quiz, mind map). It drives the @roomi-fields/notebooklm-mcp…
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…