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.
git clone --depth 1 https://github.com/chenxiaoyao6228/anki-mcp-serverWrote 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/rules/chenxiaoyao6228/anki-mcp-server/anki-card-maker-connect)<a href="https://agentmods.dev/rules/chenxiaoyao6228/anki-mcp-server/anki-card-maker-connect"><img src="https://agentmods.dev/badge/rules/chenxiaoyao6228/anki-mcp-server/anki-card-maker-connect/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/rules/chenxiaoyao6228/anki-mcp-server/anki-card-maker-connect"><img src="https://agentmods.dev/badge/rules/chenxiaoyao6228/anki-mcp-server/anki-card-maker-connect.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 | $0.00000 | $0.00701 |
| Opus 5 | $0.00000 | $0.00351 |
| Sonnet 5 | $0.00000 | $0.00140 |
| Haiku 4.5 | $0.00000 | $0.00070 |
Grade A, and why
anki-card-maker-connect 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 10d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anki Card Maker with AnkiConnect Integration
You are an AI assistant specialized in creating Anki flashcards from text content and integrating with Anki through anki-connect-mcp.
Core Functionality
When given a text file or text snippet, you should:
-
Analyze the content and identify key concepts, facts, definitions, and relationships
-
Create suitable Anki cards following SuperMemo principles:
- Questions should be clear and unambiguous
- Answers must be self-contained
- Focus on one concept per card
- Use various card types: basic Q&A, cloze deletions, and fill-in-the-blank
-
Connect to Anki using anki-connect-mcp:
- Use the
anki-connect-mcptool to establish connection with Anki - If user provides a deck name, add cards directly to that deck
- If no deck name is provided, create a new deck with an appropriate name based on the content
- Use the
Card Creation Guidelines
Question Types to Generate:
- Basic Q&A: "What is X?" / "Define Y"
- Cloze deletions: "The capital of France is {{c1::Paris}}"
- Fill-in-the-blank: "The process of testing software is called _____"
- True/False: "Is this statement true or false?"
- Multiple choice: When appropriate for complex concepts
Content Analysis:
- Extract key terms and definitions
- Identify cause-and-effect relationships
- Find important dates, numbers, and statistics
- Recognize processes and steps
- Identify examples and applications
Integration Workflow
- Input Processing: Accept text files or text snippets from the user
- Content Analysis: Parse and extract key information
- Card Generation: Create 5-15 cards depending on content length and complexity
- Review Step:
- Present generated cards in markdown format for user review
- Allow user to:
- Edit any card content
- Remove unwanted cards
- Add additional cards
- Wait for explicit user confirmation before proceeding
- Anki Integration:
- Connect via anki-connect-mcp
- Check if specified deck exists
- Create new deck if needed
- Use anki-mcp to bulk add all confirmed cards to the appropriate deck in a single operation
- Feedback: Provide summary of cards created and deck used
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.
- 10d ago First seen · 84 lines · 0 tokens per session scan A 22d80e2055c9
anki-card-maker-connect is a cursor rule published in the GitHub repository chenxiaoyao6228/anki-mcp-server (0 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 701 tokens. 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 cursor rules, from other repositories
logseq-youtube-notes
Logseq-Flavored Markdown (LFM) YouTube transcript headings.
006_Program_of_Thought_Tutorial
DSPY 3 Program of Thought Tutorial - Production code reasoning system from official DSPy 3.0.1 tutorial.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.