schedule-monte-carlo

schedule-monte-carlo is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 103 tokens per session (811 once invoked), scanned A, original, MIT.

A schedule simulation that models project completion as a range of possible dates instead of one fixed estimate. It runs many versions of the task plan, including dependencies and optimistic, likely, and pessimistic estimates.

In plain words
What is it for?
Use it to set realistic project commitments, compare a simple finish date with probability-based dates, and find the tasks that deserve management attention.
Why use it?
Adding likely estimates can hide delays because parallel work finishes when the slowest branch finishes. This shows the chance of finishing by different dates and which tasks most often control the timeline.

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/schedule_sim.py run schedule.xlsx --tasks tasks.json --sims 5000.

Good fit Use it to set realistic project commitments, compare a simple finish date with probability-based dates, and find the tasks that deserve management attention.

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 · 1,352 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/schedule-monte-carlo

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 schedule-monte-carlo

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/schedule-monte-carlo"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/schedule-monte-carlo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 811 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 $0.00103 $0.00811
Opus 5 $0.00051 $0.00405
Sonnet 5 $0.00021 $0.00162
Haiku 4.5 $0.00010 $0.00081

Measured 7d ago against content hash 434f53b3f6a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

schedule-monte-carlo 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 7d 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/schedule-monte-carlo/schedule-monte-carlo.mdc · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Schedule Monte Carlo

Summing the "likely" estimates systematically understates the finish: parallel branches mean the slowest path wins each roll, and that maximum is always worse than the middle. This skill runs the actual simulation — thousands of schedule rolls over the dependency graph — and reports the date the way it behaves: as percentiles.

Required Inputs

  • The task list with three-point estimates — per task: optimistic / likely / pessimistic (any consistent unit) and dependencies. Honest pessimistics are the whole game: "what if the API vendor ghosts us for two weeks" belongs in that number.
  • Simulation count and seed (optional; defaults 5,000 and a fixed seed — results are reproducible).

Output Format

  1. The headline gap — deterministic finish (sum-of-likelies) vs P50 vs P90, side by side. The deterministic-to-P50 gap is the lie the old plan told; show it first.
  2. The commitment guidance — promise P50 internally, P90 externally; the space between is the honesty budget. Name the dates.
  3. Criticality table — per task, the share of simulations where it sat on the critical path. The top 2-3 are where management attention belongs; a task at 0.9 criticality with a wide estimate range is the schedule.
  4. Model limits — no resource contention or calendar effects; real schedules are worse, so these are optimistic floors.

Programmatic Helper

Ships scripts/schedule_sim.pyzero dependencies, cycle-detecting, deterministic:

python3 scripts/schedule_sim.py run schedule.xlsx --tasks tasks.json --sims 5000
# tasks.json: [{"name":"design","optimistic":3,"likely":5,"pessimistic":10,"depends":[]}, …]

Prints deterministic=21.0 P10=22.3 P50=27.0 P90=32.3 · top critical: design, integrate… and writes the summary + criticality sheets. Requires a code-execution environment.

Quality Checks

  • The simulation ran (output quoted); percentiles were never eyeballed
  • The deterministic-vs-P50 gap is stated explicitly and first — it is the finding most rooms need
  • Criticality is reported per task and drives the "watch these" recommendation
  • Pessimistic estimates were interrogated: if every task's pessimistic is likely×1.2, say the inputs are optimistic theatre and the output inherits it
  • Internal-vs-external commitment dates are both named

Read the full file on GitHub · 49 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. 7d ago First seen · 49 lines · 103 tokens per session scan A 434f53b3f6a4

Subscribe to this mod's changes

schedule-monte-carlo is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 3d ago), licensed MIT. It adds 103 tokens to every session and 811 once invoked, about $0.0005 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 2026-09-03.