cash-flow-forecast

cash-flow-forecast is a cursor rule for Cursor from mohitagw15856/pm-claude-skills. It costs 99 tokens per session (946 once invoked), scanned A, original, MIT.

A week-by-week cash forecast, commonly covering 13 weeks, that tracks starting cash, expected money in, scheduled money out, and the resulting balance. It shows when cash may become tight.

In plain words
What is it for?
Structuring a cash-flow model, entering actual balances and assumptions, comparing inflows with outflows, and finding the lowest-cash point.
Why use it?
A business can be profitable on paper yet still run out of money when bills are due. This forecast makes upcoming shortfalls visible so they can be planned for earlier.

Cursor rule for Cursor

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

Good fit Structuring a cash-flow model, entering actual balances and assumptions, comparing inflows with outflows, and finding the lowest-cash point.

Compare 6 cursor rules from other repositories ↓
Install with agentmods
npx agentmods add rules/mohitagw15856/pm-claude-skills/cash-flow-forecast
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 · 1,357 stars · on GitHub · mohitagw15856.github.io

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.

Clone the repo
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills

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 cash-flow-forecast

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

Your own site · 80×15
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/cash-flow-forecast"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/cash-flow-forecast.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 99 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 946 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 $0.00099 $0.00946
Opus 5 $0.00049 $0.00473
Sonnet 5 $0.00020 $0.00189
Haiku 4.5 $0.00010 $0.00095

Measured 8d ago against content hash 2228f7ab5deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

cash-flow-forecast 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 8d 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-accounting/cash-flow-forecast/cash-flow-forecast.mdc · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cash Flow Forecast Skill

Profit is an opinion; cash is a fact — and businesses fail by running out of it even while "profitable". A short-term (commonly 13-week) cash flow forecast shows, week by week, whether money coming in covers money going out, and when the tightest point hits. This skill builds that forecast's structure and math so you can see trouble early and act.

Note: this is a planning aid, not financial, investment, or accounting advice. It structures a forecast from figures you provide and projects from your assumptions; it does not guarantee outcomes. Confirm material decisions with a qualified accountant/advisor. Never invent actual balances or amounts.

Working from a brief

Given "build me a 13-week cash flow", produce the full structure anyway — lay out the model with the formulas and a worked example using placeholder figures (replace with your numbers). Use the real numbers where the user gave them; never fabricate a starting balance or a result.

Required Inputs

Ask for these only if they aren't already provided (else use labelled placeholders):

  • Starting cash — current bank balance (the opening position).
  • Inflows — expected receipts and their timing (customer payments, with realistic collection timing, not invoice date).
  • Outflows — scheduled payments and timing (payroll, rent, suppliers, loan repayments, tax, subscriptions).
  • Horizon & purpose — 13 weeks (default) or other, and what decision it informs (a crunch, a hire, a raise).

Output Format

13-Week Cash Flow Forecast: [business]

  • How it works — the model in one line: Closing cash = Opening cash + Inflows − Outflows, run week over week (each week's closing is the next week's opening).
  • Forecast table — a week-by-week layout (template + a worked example with placeholder figures):
Week Opening cash Inflows Outflows Net Closing cash

Break inflows/outflows into their main lines (receipts; payroll, rent, suppliers, tax…) so it's actionable.

  • Key read-outs — the lowest cash point and which week it hits, weeks that go negative (the warning), and total net movement over the horizon.
  • Assumptions — collection timing, what's committed vs. expected, and anything to confirm — stated explicitly (the forecast is only as good as these).
  • If cash goes tight — levers — accelerate receivables, delay/stagger payables, cut/defer discretionary spend, draw on credit, or raise — with the trade-offs.

Read the full file on GitHub · 70 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. 8d ago First seen · 70 lines · 99 tokens per session scan A 2228f7ab5deb

Subscribe to this mod's changes

cash-flow-forecast is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 946 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.