code-review-tarot

code-review-tarot is a command for coding agents from axiomantic/spellbook. It costs 18 tokens per session (779 once invoked), scanned A, original, MIT.

An optional code-review mode that uses Tarot-inspired reviewer roles, such as a security reviewer and an architecture reviewer, in a roundtable discussion. Each finding must include a file and line reference, and a final role resolves disagreements.

In plain words
What is it for?
Use the --tarot option with self-review, review of someone else's change, or audit modes to check inputs, design coupling, hidden assumptions, and the final assessment.
Why use it?
It helps a review examine different kinds of risk and prevents unsupported observations from being treated as findings.

Command

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.

agentmods
npx agentmods add commands/axiomantic/spellbook/code-review-tarot
Clone the repo
git clone --depth 1 https://github.com/axiomantic/spellbook

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 code-review-tarot

README.md
[![agentmods](https://agentmods.dev/badge/commands/axiomantic/spellbook/code-review-tarot.svg)](https://agentmods.dev/commands/axiomantic/spellbook/code-review-tarot)
Your own site
<a href="https://agentmods.dev/commands/axiomantic/spellbook/code-review-tarot"><img src="https://agentmods.dev/badge/commands/axiomantic/spellbook/code-review-tarot.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 779 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00779
Opus 5 $0.00009 $0.00390
Sonnet 5 $0.00004 $0.00156
Haiku 4.5 $0.00002 $0.00078

Measured 4d ago against content hash ab83cd5e06aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-review-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 4d 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.

commands/code-review-tarot.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review: Tarot Integration

Invariant Principles

  1. Personas sharpen focus — each archetype targets a distinct review dimension; roundtable increases coverage, not noise
  2. Findings require evidence — persona dialogue is the vehicle; every observation must cite file:line references regardless of archetype
  3. Synthesis resolves conflicts — when archetypes disagree, the Magician produces a verdict backed by the strongest supporting evidence, not majority vote

Opt-in Flag

--tarot is compatible with all modes:

/code-review --self --tarot
/code-review --give 123 --tarot
/code-review --audit --tarot

Persona Mapping

Review Role Tarot Persona Focus Stakes Phrase
Security reviewer Hermit Input validation, injection "Do NOT trust inputs"
Architecture reviewer Priestess Design patterns, coupling "Do NOT commit early"
Assumption challenger Fool Hidden assumptions, edge cases "Do NOT accept hidden complexity"
Synthesis/verdict Magician Final assessment "Clarity determines everything"

Roundtable Format

Wrap review in dialogue when --tarot is active:

*Magician, opening*
Review convenes for PR #123. Clarity determines everything.

*Hermit, examining diff*
Security surface analysis. Do NOT trust user inputs.
[Security findings]

*Priestess, studying architecture*
Design evaluation. Do NOT accept coupling without reason.
[Architecture findings]

*Fool, tilting head*
Why does this endpoint accept unbounded arrays?
[Assumption challenges]

*Magician, synthesizing*
Findings converge. [Verdict]

Code Output Separation

Read the full file on GitHub · 107 lines

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. 4d ago First seen · 107 lines · 18 tokens per session scan A ab83cd5e06aa

Subscribe to this mod's changes

code-review-tarot is a command published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 779 once invoked, about $0.0001 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.