decision-tree-solver

decision-tree-solver is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 115 tokens per session (1,448 once invoked), scanned A, original, MIT.

A decision-analysis tool that turns a choice into a tree of options, chances, outcomes, and costs. It calculates the expected value of each path and the probability at which the recommendation changes.

In plain words
What is it for?
Use it to compare choices such as settling or going to trial, launching or waiting, or fixing or replacing something. It helps identify the assumptions that determine the decision.
Why use it?
It replaces vague arguments about uncertain choices with visible arithmetic. The break-even probability shows how confident you must be before one option becomes preferable.

Cursor rule for Cursor

Written for Cursor: a Cursor rule (.mdc).

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 scripts/decision_tree.py --input tree.json # tree with EVs and best choices.

Good fit Use it to compare choices such as settling or going to trial, launching or waiting, or fixing or replacing something. It helps identify the assumptions that determine the decision.

Compare 6 cursor rules from other repositories ↓
About the project

PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.

mohitagw15856/pm-claude-skills · 1,345 stars · on GitHub · mohitagw15856.github.io

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills
agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/decision-tree-solver

Made for: Cursor.

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 decision-tree-solver

README.md
[![agentmods](https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/decision-tree-solver/github.svg)](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/decision-tree-solver)
Your own site
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/decision-tree-solver"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/decision-tree-solver/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.

agentmods 80×15 button for decision-tree-solver

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/decision-tree-solver"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/decision-tree-solver.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 115 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,448 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00115 $0.01448
Opus 5 $0.00057 $0.00724
Sonnet 5 $0.00023 $0.00290
Haiku 4.5 $0.00012 $0.00145

Measured 4d ago against content hash 269a889a8e6a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

decision-tree-solver 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.

exports/cursor/pm-calculators/decision-tree-solver/decision-tree-solver.mdc · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Decision Tree Solver

"Should we settle or go to trial" is not answered by instinct or by whoever argues longest — it is three numbers and a probability, and most people have never actually multiplied them. This skill extracts the tree hiding inside a messy decision (the choices, the chances, the payoffs, the costs of playing), computes the rollback with the bundled script, and — the part instinct can never do — finds the break-even: the probability at which the recommendation flips. Because "trial is worth it if you win 60% of the time" is an opinion, but "the answer flips at 90% — are you more than 90% sure?" is a decision made tractable. The script is deterministic, stdlib-only, and shows its arithmetic.

What This Skill Produces

  • The extracted tree — decisions, chance nodes with probabilities, outcomes with values, and the costs of each path, pulled from the situation as described
  • The rollback — expected value at every node, the best choice named at every fork, from the script
  • The break-even scan — for each two-way uncertainty, the probability at which the top-level choice flips, which is the number that makes probability arguments productive
  • The robustness read — whether the answer survives the probabilities being argued about, or hinges on a number nobody can defend
  • The leaves-out list — what expected value cannot see here: risk appetite, one-shot vs repeated, the unquantified costs

Required Inputs

Ask for these if not provided:

  • The choices — the real options on the table, including the do-nothing one
  • The uncertainties — what could happen under each choice, and the requester's honest probability for each (pushing back on false precision is part of the job)
  • The payoffs and costs — the money (or a stated proxy) at each end point, and what each path costs to walk: fees, time priced honestly, deposits
  • The stakes context — one-shot or repeatable, and whether the worst branch is survivable — because expected value is the right tool for repeatable bets and needs a caveat for ruinous one-shots

Read the full file on GitHub · 77 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 · 77 lines · 115 tokens per session scan A 269a889a8e6a

Subscribe to this mod's changes

decision-tree-solver is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,345 stars, last pushed 2d ago), licensed MIT. It adds 115 tokens to every session and 1,448 once invoked, about $0.0006 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 2026-09-05.