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 whateverforever/maxs-claude-skills --skill anki-cardsgit clone --depth 1 https://github.com/whateverforever/maxs-claude-skillsWrote 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/whateverforever/maxs-claude-skills/anki-cards)<a href="https://agentmods.dev/skills/whateverforever/maxs-claude-skills/anki-cards"><img src="https://agentmods.dev/badge/skills/whateverforever/maxs-claude-skills/anki-cards/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/whateverforever/maxs-claude-skills/anki-cards"><img src="https://agentmods.dev/badge/skills/whateverforever/maxs-claude-skills/anki-cards.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 | $0.00137 | $0.02440 |
| Opus 5.5 | $0.00055 | $0.00976 |
| Sonnet 5.5 | $0.00027 | $0.00488 |
| Haiku 4.5 | $0.00014 | $0.00244 |
Grade A, and why
anki-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 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Anki Flashcard Generator
Turn conversation content into high-quality Anki flashcards, exported as a TSV file ready for import.
Workflow
1. Gather Parameters
When the user asks for Anki cards, ask two things before generating:
-
How many cards? — Ask for a target number. If the conversation is short, suggest a reasonable range (e.g., "This conversation covered ~3 key topics — I'd suggest 5–10 cards. How many would you like?").
-
One-sided or double-sided? — Default suggestion is one-sided. Briefly explain the double-sided option:
- One-sided (default): Front = question, Back = answer.
- Double-sided: Both sides are questions. Knowing either side lets you recall the other. Example:
- Front: "What flag has red crosses on a white background?"
- Back: "How does the flag of Georgia look?"
2. Extract Key Facts from the Conversation
Review the conversation and identify the facts, concepts, distinctions, and relationships that the user would benefit from memorizing. Focus on:
- New information the user learned (things they asked about or expressed surprise at)
- Core concepts and definitions
- Key distinctions or comparisons discussed
- Concrete facts (names, numbers, dates, formulas, commands)
- Cause-and-effect relationships
- Corrections or misconceptions that were cleared up
Ignore: pleasantries, meta-discussion about the conversation itself, tangential remarks, and anything the user clearly already knew.
3. Write Cards Following Best Practices
Every card must follow these principles:
Minimum Information Principle
Each card tests exactly one atomic fact or association. Never combine multiple facts into a single card.
- BAD: "What are the three types of heat transfer?" → "Conduction, convection, and radiation"
- GOOD: Three separate cards, each asking about one type, or each asking what category a given type belongs to.
No Orphan Cards
Every card must contain enough context to be understood in isolation, months later, without remembering the original conversation. Add brief context cues where needed.
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 · 174 lines · 137 tokens per session scan A 6259a51f7497
anki-cards is a skill published in the GitHub repository whateverforever/maxs-claude-skills (3 stars, last pushed 6mo ago), licensed MIT. It adds 137 tokens to every session and 2,440 once invoked, about $0.0005 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
academy-guide
Stop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude…
radical-candor
Stop being a "nice" manager. Learn Kim Scott's framework for caring personally while challenging directly—the combination that builds trust and drives performance. Use when: Giving feedback (positive or constructive); Building trust with direct reports; Performance conversations that need to happen; Team culture…
educational-presentation
Transform Claude into an expert in evidence-based educational presentation design. Use when designing presentations for teaching, training, or learning contexts where retention and comprehension matter. Applies Cognitive Load Theory, Mayer's 12 Principles of Multimedia Learning, Gagné's 9 Events of Instruction…
first-principles
Break down complex problems to their fundamental truths, then reason up from there. Master Aristotle's ancient method modernized by Elon Musk to solve seemingly impossible problems. Use when: Facing a "impossible" problem where conventional solutions don't work; Challenging industry assumptions that everyone accepts…
one-on-ones
Design and run effective 1:1 meetings that build trust, develop people, and surface problems early. Covers cadence setup, agenda ownership, conversation frameworks, question banks, and handling difficult topics. Use when: a new manager learning to run 1:1s, resetting unproductive 1:1s that became status updates…
rwkv-architecture
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.