anki

anki is a skill for Claude Code, Codex from terkelg/anki-markdown. It costs 79 tokens per session (2,124 once invoked), scanned A, original, MIT.

A tool for creating and managing Anki flashcards. Anki is a learning application that uses spaced repetition, showing cards again at intervals intended to support memorization.

In plain words
What is it for?
Use it to create cards, add notes to decks, update or delete notes with confirmation, and rate cards during review.
Why use it?
It turns information into reviewable cards and can manage them through AnkiConnect, the connection used by external tools to communicate with Anki. Cards must be reviewed before they are added.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create cards, add notes to decks, update or delete notes with confirmation, and rate cards during review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terkelg/anki-markdown/anki
Install

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.

Any agent
npx skills add terkelg/anki-markdown --skill anki
Clone the repo
git clone --depth 1 https://github.com/terkelg/anki-markdown

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for anki

README.md
[![agentmods](https://agentmods.dev/badge/skills/terkelg/anki-markdown/anki.svg)](https://agentmods.dev/skills/terkelg/anki-markdown/anki)
Your own site
<a href="https://agentmods.dev/skills/terkelg/anki-markdown/anki"><img src="https://agentmods.dev/badge/skills/terkelg/anki-markdown/anki.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,124 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 26 Apr 2026
  • Snyk pass 26 Apr 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.02124
Opus 5 $0.00039 $0.01062
Sonnet 5 $0.00016 $0.00425
Haiku 4.5 $0.00008 $0.00212

Measured 8d ago against content hash 0e302eae1bd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

anki scanned grade A with 1 finding 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/anki.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Ensure `curl` and `jq` are available in PATH
skills/anki/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Anki Flashcard Management

Use the anki.sh script to create and manage flashcards via AnkiConnect.

ANKI="$(dirname "$SKILL_PATH")/scripts/anki.sh"

Preflight:

  • Ensure Anki desktop is running with AnkiConnect enabled
  • Ensure curl and jq are available in PATH

CRITICAL: User Approval Required

NEVER add cards to Anki without explicit user approval.

Before adding any cards:

  1. Display all proposed cards in full (front + back)
  2. Ask user to confirm: "Ready to add these cards?"
  3. Only proceed after explicit "yes" / approval

This is non-negotiable. Users must review card quality before adding.

For potentially destructive or irreversible actions:

  • delete: ask explicit confirmation before deleting notes
  • update: confirm exact fields/IDs before updating notes
  • rate: show card + suggested rating, then wait for user confirmation before submitting

Guidelines

  • MUST use the Anki Markdown note type for basic cards or Anki Markdown Cloze for cloze deletions
  • Use markdown for both front and back fields
  • Test exactly one fact or idea per card
  • Make questions atomic and simple
  • Keep questions and answers short, clear, and unambiguous
  • Ensure each card has one unique, specific answer
  • Avoid long lists or multiple items in one card
  • Add context or hints so your future self understands
  • Personalize with examples or mnemonics if helpful
  • Allow multiple simple cards for important concepts
  • Create multiple variants of important questions from different angles
  • Connect cards to personal goals and projects to avoid "orphan" facts
  • Always use syntax highlighting for code (see Code Snippets section)
  • When creating multiple related cards, use bulk operations for efficiency

Choosing Card Type

Use Anki Markdown (Front/Back) for question-answer pairs where you write a specific question. Use Anki Markdown Cloze (Text/Extra) for fill-in-the-blank cards where hiding parts of a statement is more natural than writing a question.

Read the full file on GitHub · 232 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 8d ago First seen · 232 lines · 79 tokens per session scan A 0e302eae1bd4

Subscribe to this mod's changes

anki is a skill published in the GitHub repository terkelg/anki-markdown (42 stars, last pushed 2mo ago), licensed MIT. It adds 79 tokens to every session and 2,124 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.