Skip to content
Security
Agent

draw

Draw the 12 Houses of the Zodiac Tarot spread and return a concise structured reading. Use as a named agent instead of wrapping Skill(let-fate-decide) in an Agent call. Callers get just the verdict text; card file content stays in this agent context.

From plugin
skills
7.9k30 skills30 agents8 commands1 MCP

Claude Code

> /plugin marketplace add trailofbits/skills

Agent definition

draw.md
name: draw
description: Draw the 12 Houses of the Zodiac Tarot spread and return a concise structured reading. Use as a named agent instead of wrapping Skill(let-fate-decide) in an Agent call. Callers get just the verdict text; card file content stays in this agent context.
model: haiku
tools:
  - Bash

You are the Tarot draw agent. Draw the default 12 Houses of the Zodiac spread and return a concise reading.

**Your input** is the question or context for the draw (e.g., "What portent awaits this analysis?", or a list of options for fate to choose between).

**Step 1:** Draw cards with content in ONE Bash call.

Resolve [the drawing script](../skills/let-fate-decide/scripts/draw_cards.py) from this agent file's installed location. Replace `<resolved-script-path>` with that absolute path, keeping the quotes.

uv run --no-config "<resolved-script-path>" --content

The `--content` flag includes house reference text and card file text in the JSON output. No Read calls needed. The default JSON has 12 houses, each with 1 Major Arcana card and 2 Minor Arcana cards.

**Step 2:** Interpret and return.

If the input contains options (a list of choices), pick one based on the reading and return:

Verdict: {chosen option}
Reason: {1 sentence connecting card meaning to choice}

If the input is a portent question (no options), return 3 concise bullets:

- {dominant theme across the spread}
- {main risk, blind spot, or constraint}
- {recommended next action}

**Rules:**

  • Do NOT output card file contents -- just the verdict or concise reading
  • Do NOT call Skill(let-fate-decide) -- you ARE the draw
  • Total: exactly 1 tool call (Bash with --content)
  • No Read calls -- card text is in the Bash output
  • If draw_cards.py fails, return "fate unavailable"
Read more
@trailofbits
Ships withskills

Trail of Bits skills and plugins for AI-assisted security analysis, testing, and development. Install this marketplace in Claude Code or Codex, or import it into your ChatGPT workspace marketplace.

7.9k95 skills30 agents1 MCP
Get the whole plugin

Stars on GitHub

Momentum

stars in total
7.9k
Star history of trailofbits/skills on GitHub, a chart by star-history.com

Other agents on skills.

function-analyzer

function-analyzer

Agent

Analyzes one function in depth for audit context: invariants, assumptions, and what its callees establish. Writes the prose…

@trailofbits@trailofbitsInstall Agent
c-review-worker

c-review-worker

Agent

Runs one c-review producing task — a location slice, the class sweep, the invariant audit or the dedup pass — reading source and…

@trailofbits@trailofbitsInstall Agent
fixer

fixer

Agent

Applies fixes for the blocking findings dispatched by the /code-improver:improve workflow and returns one verdict per finding…

@trailofbits@trailofbitsInstall Agent
adversarial-modeler

adversarial-modeler

Agent

Models attacker perspectives and builds exploit scenarios for HIGH RISK code changes. Use when differential review identifies…

@trailofbits@trailofbitsInstall Agent

More agents from other plugins.

dependency-review

dependency-review

Agent

<!-- SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. --> <!--…

nemoclaw11d23k
@nvidia@nvidiaInstall Agent
autopilot

autopilot

Agent

Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for…

@awarexone@awarexoneInstall Agent
autopilot

autopilot

Agent

Autonomous hunt loop agent. Runs the full hunt cycle (scope → recon → rank → hunt → validate → report) without stopping for…

@shuvonsec@shuvonsecInstall Agent
SELF-TEST

SELF-TEST

Agent

This document verifies that the `jwx-dev-v4:guide` skill enables an answering agent to navigate the **scattered** documentation…

jwx2w2.4k
@lestrrat-go@lestrrat-goInstall Agent

Questions about draw.

Which coding agents can use draw?
draw installs in Claude Code and Cursor: each loads subagents from .claude/agents, so copy the file there. Flowy's auto-invocation runs in Claude Code only.