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 benbenzhangai/claude-tarot-skill --skill tarot-reflectiongit clone --depth 1 https://github.com/benbenzhangai/claude-tarot-skillWrote 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/benbenzhangai/claude-tarot-skill/tarot-reflection)<a href="https://agentmods.dev/skills/benbenzhangai/claude-tarot-skill/tarot-reflection"><img src="https://agentmods.dev/badge/skills/benbenzhangai/claude-tarot-skill/tarot-reflection/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/benbenzhangai/claude-tarot-skill/tarot-reflection"><img src="https://agentmods.dev/badge/skills/benbenzhangai/claude-tarot-skill/tarot-reflection.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 | $0.00116 | $0.01735 |
| Opus 5.5 | $0.00046 | $0.00694 |
| Sonnet 5.5 | $0.00023 | $0.00347 |
| Haiku 4.5 | $0.00012 | $0.00173 |
Grade A, and why
tarot-reflection 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 2mo 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tarot Reflection Reading (Decision Support)
This skill provides structured, reflective tarot readings that support decision-making and personal insight while maintaining epistemic humility and encouraging real-world verification.
Core Workflow
Follow these steps for every reading:
1. Clarify the Question
Parse the user's request into a clear decision or reflection frame:
- Decision support: "Should I take this job?" → Frame as exploring dynamics around career change
- Relationship inquiry: "What's happening with X?" → Frame as understanding relationship dynamics
- Personal growth: "What do I need to know?" → Frame as reflection on current life chapter
If the question is vague, propose a clarified frame and confirm before proceeding.
2. Select the Spread
Choose based on complexity and question type:
1-card: Single-focus questions, daily guidance, quick check-ins
3-card (Past/Present/Future): Timeline-based questions, understanding progression
3-card (Situation/Action/Outcome): Action-focused decisions
5-card (Decision): Comparing two paths or complex choices
Celtic Cross: Multi-faceted situations requiring deep exploration
If user specifies a spread, use it. Otherwise, suggest the most appropriate one.
3. Draw or Receive Cards
If user provides cards: Skip drawing, proceed to interpretation
If drawing needed: Use scripts/tarot_deck.py with appropriate parameters
from scripts.tarot_deck import draw_cards, format_draw, get_spread
# Example: 3-card reading with reversals
cards = draw_cards(3, seed=None, allow_reversals=True)
positions = get_spread("3-card-past-present-future")
reading = format_draw(cards, positions)
Reversal handling: Default to allowing reversals unless user requests "no reversals" or "upright only"
4. Interpret Each Card (Position-Aware)
For each card, consult references/card_meanings.md and synthesize:
- Card's core themes (from reference)
- Position context (what this position asks)
- Orientation (upright vs reversed if applicable)
- Question relevance (how it applies to user's specific situation)
What ships with it
2 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.
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.
- 2mo ago First seen · 221 lines · 116 tokens per session scan A dfc299b89f50
tarot-reflection is a skill published in the GitHub repository benbenzhangai/claude-tarot-skill (8 stars, last pushed 9mo ago), licensed MIT. It adds 116 tokens to every session and 1,735 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.
tarot-reflection compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tarot-reflectionbenbenzhangai/claude-tarot-skill | Skill | 8 | 9mo ago | MIT | A | 116 | Claude Code, Codex |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 56k | 6d ago | MIT | A | 83 | Claude Code |
| webhook-managementhoangsonww/Claude-Code-Agent-Monitor | Skill | 1.2k | yesterday | MIT | A | 56 | Claude Code, Codex |
| gesellschaftsrechtliche-satzungen-agbKlotzkette/claude-fuer-deutsches-recht | Skill | 1.8k | yesterday | Apache-2.0 | A | 69 | Claude Code |
| render-3d-product-showcasegooseworks-ai/goose-skills | Skill | 1.3k | yesterday | MIT | A | 159 | Claude Code, Codex |
| render-airdrop-carouselgooseworks-ai/goose-skills | Skill | 1.3k | yesterday | MIT | A | 207 | Claude Code, Codex |
| accessibility-patternsvibeeval/vibecosystem | Skill | 539 | 3d ago | MIT | A | 24 | Claude Code, Codex |