forecast-engine

forecast-engine is a skill for Claude Code from alexgrebeshok-coder/ai-pmo-skills. It costs 61 tokens per session (2,177 once invoked), scanned A, original, MIT.

A project forecasting guide for estimating the final completion date, total cost, remaining work, and chances of meeting targets. It uses current project performance, trends, and simulated scenarios such as Monte Carlo analysis.

In plain words
What is it for?
Use it to calculate expected final cost, remaining cost, completion dates, what-if scenarios, and probabilities of finishing on schedule or within budget.
Why use it?
It helps replace a simple current-status view with estimates of where the project is likely to finish in time and cost.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ai-pmo-skills plugin — 11 skills shipped together

Good fit Use it to calculate expected final cost, remaining cost, completion dates, what-if scenarios, and probabilities of finishing on schedule or within budget.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine
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.

Any agent
npx skills add alexgrebeshok-coder/ai-pmo-skills --skill forecast-engine
Clone the repo
git clone --depth 1 https://github.com/alexgrebeshok-coder/ai-pmo-skills

Made for: Claude Code.

Or install ai-pmo-skills, the plugin that ships this one along with the rest of its 11 skills.

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 forecast-engine

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine/github.svg)](https://agentmods.dev/skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine)
Your own site
<a href="https://agentmods.dev/skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine"><img src="https://agentmods.dev/badge/skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine/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 forecast-engine

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine"><img src="https://agentmods.dev/badge/skills/alexgrebeshok-coder/ai-pmo-skills/forecast-engine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,177 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 $0.00061 $0.02177
Opus 5 $0.00030 $0.01089
Sonnet 5 $0.00012 $0.00435
Haiku 4.5 $0.00006 $0.00218

Measured 11d ago against content hash aa34ac02b0fb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

forecast-engine 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 11d 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.

skills/forecast-engine/SKILL.md · 249 lines

How it starts

The opening of the file, as written. The whole thing — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Forecast Engine — Прогнозирование проекта

Назначение

Прогнозирование ключевых параметров проекта:

  • Срок завершения (EAC Date)
  • Итоговая стоимость (EAC Cost)
  • Остаток работ (ETC)
  • Сценарный анализ "что если"
  • Вероятность завершения в срок/бюджет

Методы прогнозирования

1. EVM-based (Earned Value)

EAC (Estimate at Completion) — Прогноз итоговой стоимости:

Метод Формула Когда использовать
Типичный EAC = BAC / CPI Текущая эффективность сохранится
Атипичный EAC = AC + (BAC - EV) Отклонение разовое, дальше по плану
Комбинированный EAC = AC + (BAC - EV) / (CPI × SPI) Отклонения и по срокам, и по стоимости

ETC (Estimate to Complete) — Сколько осталось:

ETC = EAC - AC

2. Trend-based (По тренду)

Анализ скорости выполнения за последние N периодов:

Средняя скорость = Σ(Выполнено за период) / N периодов
Остаток работ = 100% - Текущий %
Прогноз завершения = Сегодня + (Остаток / Скорость)

3. Monte Carlo (Вероятностный)

Симуляция 1000+ сценариев с учётом:

  • Разброса длительностей (оптимист/пессимист)
  • Корреляции между задачами
  • Вероятности рисков

Результат: распределение вероятностей завершения

Workflow

Шаг 1: Сбор данных

Из progress-tracker получаем:

  • Плановые показатели (PV, BAC)
  • Фактические показатели (EV, AC)
  • Историю выполнения (тренд)

Шаг 2: Расчёт прогнозов

# Базовые расчёты EVM
BAC = 10_000_000  # Бюджет
AC = 4_800_000   # Фактические затраты
EV = 4_500_000   # Освоенный объём

CPI = EV / AC  # 0.9375
SPI = EV / PV  # 0.90

# Прогноз стоимости (типичный)
EAC = BAC / CPI  # 10_666_667 ₽

# Прогноз остатка
ETC = EAC - AC  # 5_866_667 ₽

# Отклонение от бюджета
VAC = BAC - EAC  # -666_667 ₽ (перерасход)

Шаг 3: Прогноз сроков

# На основе SPI
плановый_срок = 180  # дней
прошло = 90  # дней
выполнено = 45%  # по факту

# Прогноз при текущем темпе
оставшийся_срок = (100% - 45%) / (45% / 90 дней)
# = 55% / 0.5%/день = 110 дней

прогноз_завершения = сегодня + 110 дней
отклонение = (90 + 110) - 180 = +20 дней

Read the full file on GitHub · 249 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. 11d ago First seen · 249 lines · 61 tokens per session scan A aa34ac02b0fb

Subscribe to this mod's changes

forecast-engine is a skill published in the GitHub repository alexgrebeshok-coder/ai-pmo-skills (10 stars, last pushed 6mo ago), licensed MIT. It adds 61 tokens to every session and 2,177 once invoked, about $0.0003 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.

Related

Other skills, from other repositories