A guided tarot-reading method that treats tarot cards as a tool for symbolic reflection rather than a prediction engine. It can use a physical draw supplied by the user or perform a programmed draw.

Interpreting a tarot draw, reflecting on decisions or creative blocks, reviewing a project, and turning card meanings into situation analysis and practical guidance.

It gives personal, creative, or project questions a structured way to examine situations while avoiding claims of certainty. It also sets limits for medical, legal, financial, emergency, and crisis advice.

tarot — Skill for Codex by sapuyou45-bit

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 sapuyou45-bit/oraclebone --skill tarot

Clone the repo

git clone --depth 1 https://github.com/sapuyou45-bit/oraclebone

Made for: 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sapuyou45-bit/oraclebone/tarot/github.svg)](https://agentmods.dev/skills/sapuyou45-bit/oraclebone/tarot)

Your own site

<a href="https://agentmods.dev/skills/sapuyou45-bit/oraclebone/tarot"><img src="https://agentmods.dev/badge/skills/sapuyou45-bit/oraclebone/tarot/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sapuyou45-bit/oraclebone/tarot"><img src="https://agentmods.dev/badge/skills/sapuyou45-bit/oraclebone/tarot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 475 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.00475
Opus 5	$0.00021	$0.00237
Sonnet 5	$0.00008	$0.00095
Haiku 4.5	$0.00004	$0.00047

Measured 9d ago against content hash 9aba19f039f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tarot 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 9d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/_standalone_tarot.py, scripts/draw.py), 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.

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.

skills/tarot/SKILL.md · 57 lines

What it actually says

Tarot

Tarot is used here as a symbolic reflection tool, not a prediction engine.

When to Use

The user asks for tarot, a card pull, or a card reading.
The user wants symbolic reflection for a decision, creative block, project review, or personal question.
The user provides physical tarot cards and wants an interpretation.

When Not to Use

The request needs medical, legal, financial, emergency, or crisis advice.
The user wants a deterministic prediction or certainty about future events.
The user asks the agent to choose cards without a script or physical draw.

Workflow

Clarify the user's question if needed.
Choose a spread from references/spreads.md.
Run scripts/draw.py unless the user provides a physical draw.
Read references/interpretation-template.md before writing the interpretation.
Read references/sources.md when method or licensing rigor matters.
Read references/cards.md for concise card and suit meanings.
Interpret using the shared response contract:
- Result
- Symbolic Reading
- Situation Mapping
- Hidden Variables
- Actionable Guidance
- Boundaries

Commands

python3 scripts/draw.py --deck major --spread single
python3 scripts/draw.py --deck major --spread three-card --reversals
python3 scripts/draw.py --deck full --spread decision --reversals
python3 scripts/draw.py --spread project --seed demo

Use --seed only for tests and reproducible demos, not real readings.

Rules

Do not choose cards yourself.
Do not use seeded mode for real readings unless the user explicitly wants a reproducible demo.
Do not redraw because the first result is inconvenient.
Do not claim certainty about future events.
Do not answer medical, legal, financial, or crisis questions as a tarot verdict.
If script execution is unavailable, ask the user to provide a physical draw or say the draw cannot be performed.

Files

What ships with it

13 files 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.

9d ago First seen · 57 lines · 42 tokens per session scan A 9aba19f039f2

Subscribe to this mod's changes

tarot is a skill published in the GitHub repository sapuyou45-bit/oraclebone (4 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 475 once invoked, about $0.0002 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.

ai-agents ai-skills codex divination iching openai

divination

Runs OpenDivination's CLI for tarot, I Ching, source inspection, and provenance-aware symbolic sessions for users or agents.

amenti-labs/opendivination · 29 tokens

divination-setup

Installs or updates OpenDivination, verifies the CLI, and runs first-run source setup including QRNG credentials and QCicada selection. Use when the user wants to set up OpenDivination, bootstrap the divination skill, save a persistent source, or prepare hardware entropy.

amenti-labs/opendivination · 61 tokens

yarrow

An I-Ching consultation tool. The I-Ching, or Book of Changes, is a Chinese divination text; this tool casts a hexagram and explains it using several classical and modern sources.

shaozhengkun123/yarrow · 137 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

ax-agent-rlm

This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…

ax-llm/ax · 88 tokens

happiness-skill

A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.

kangarooking/cangjie-skill · 136 tokens