Skip to content
SkillMixed2,225 tokens in use

let-fate-decide

Draws a 12-house Tarot spread with cryptographic randomness to add entropy to vague or casually delegated prompts.

8,319 stars on the repository CC-BY-SA-4.0trailofbits/skills · plugins/let-fate-decide/skills/let-fate-decide
/plugin marketplace add trailofbits/skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing let-fate-decide costs

114tokens idle
2,225tokens in use
4,880tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Mixed

Script-ledMixedModel-led

Scripts do part of the work and the model's judgement does the rest.

This describes the skill's structure, how much of it is scripts. It does not say how well it works. Scripts: scripts/draw_cards.py, scripts/test_draw_cards.py.

Touches

shelldeclared and detected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples12/15
  • Output10/15
  • Size15/15
  • Resources14/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−2

    does this on the machine, as the frontmatter declares

    SKILL.md, line 20

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity100
  • Maintenance52
  • Community64
  • Maturity32
  • Momentum40

Let Fate Decide is a playful decision aid. When a prompt is vague, the user shrugs (“whatever”, “YOLO”, “your call”) or the agent is about to pick arbitrarily between equal options, a bundled Python script deals the 12 Houses of the Zodiac Tarot spread: one Major Arcana and two Minor Arcana cards per house, each possibly reversed.

The agent reads the house and card meaning files, interprets the whole spread, and applies it to the task. It is not meant to decide safety-critical work.

What You Get

  • A cryptographically random 12-house spread with upright and reversed cards
  • Markdown meaning files for all 78 cards and each of the 12 houses
  • An interpretation guide and technical context lenses
  • A legacy mode that deals a smaller hand
  • Rules that keep the reading advisory in security and correctness work

Common Use Cases

  • Breaking a tie between several reasonable approaches
  • Responding to a prompt such as “idk, just do something”
  • Choosing which angle of a codebase to inspect next
  • Generating hypotheses when an investigation stalls

What Makes It Unique

It treats Tarot as a source of entropy and perspective for planning, with real randomness behind the draw and an explicit rule never to fake a draw if the script fails. It also fences itself in: user requirements win over the cards, one draw is allowed per decision, and in security work the reading may pick what to inspect but only evidence can dismiss a risk.

Under The Hood

The agent runs a bundled Python script through uv in the shell. The script draws cards locally with cryptographic randomness and prints JSON; it needs no network. The agent then reads the house and card markdown files that ship with the skill and combines the interpretation with its next tool call. The skill writes no files of its own.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers