cash-flow-snapshot

cash-flow-snapshot is a skill for Claude Code from alebgl77/claude-inc. It costs 0 tokens per session (1,239 once invoked), scanned A, original, MIT.

A 13-week cash forecast built from bank data, unpaid customer invoices, unpaid bills, and recurring expenses. It shows how the cash balance may change week by week and how long the money may last.

In plain words
What is it for?
Use it to check whether payroll or other dated payments can be covered, plan hires or purchases, and decide whether to collect money faster, cut spending, or delay payments.
Why use it?
It turns scattered financial records into a short-term view of cash shortages, including the lowest expected balance and warnings about limited runway. Runway means the number of weeks the available cash can cover expected spending.

Skill for Claude Code

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

Part of the claude-inc plugin — 54 skills, 3 commands, 9 agents shipped together

Good fit Use it to check whether payroll or other dated payments can be covered, plan hires or purchases, and decide whether to collect money faster, cut spending, or delay payments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alebgl77/claude-inc/cash-flow-snapshot
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 alebgl77/claude-inc --skill cash-flow-snapshot
Clone the repo
git clone --depth 1 https://github.com/alebgl77/claude-inc

Made for: Claude Code.

Or install claude-inc, the plugin that ships this one along with the rest of its 54 skills, 3 commands, 9 agents.

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-snapshot

README.md
[![agentmods](https://agentmods.dev/badge/skills/alebgl77/claude-inc/cash-flow-snapshot/github.svg)](https://agentmods.dev/skills/alebgl77/claude-inc/cash-flow-snapshot)
Your own site
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/cash-flow-snapshot"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/cash-flow-snapshot/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-snapshot

Your own site · 80×15
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/cash-flow-snapshot"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/cash-flow-snapshot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,239 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00000 $0.01239
Opus 5 $0.00000 $0.00620
Sonnet 5 $0.00000 $0.00248
Haiku 4.5 $0.00000 $0.00124

Measured 10d ago against content hash c1e5963c5112, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

cash-flow-snapshot 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 10d 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/cash-flow-snapshot/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Cash Flow Snapshot — Cash Watcher

"Snapshot your cash."

Thirteen weeks is the horizon a small business actually lives in: long enough to see trouble coming, short enough that the numbers stay honest.

When to use

  • "How much cash do we actually have, and how long does it last?"
  • "Will we make payroll on the 15th?" — any survival question pinned to a date.
  • "Here's our bank export and open invoices — what's coming?"
  • Before any decision that moves real money: a hire, a bulk order, new equipment, a lease.
  • On a schedule: monthly when healthy, weekly when tight.

Workflow

  1. Collect inputs. Take pasted data or files: current balance of every cash account, open receivables (client, amount, due date), open payables (vendor, amount, due date), and recurring items (payroll, rent, loans, subscriptions). A raw bank CSV works — derive the recurring pattern from 3+ months of history.
  2. Set the opening balance. Sum all cash accounts as of today and state the as-of date explicitly. This is the anchor every other number hangs from.
  3. Tier the inflows. Committed = invoiced with a due date or contractually scheduled. Likely = recurring history or a firm verbal agreement. Hopeful = pipeline and wishes. Never blend the tiers.
  4. Map the outflows. Fixed (payroll, rent, loan payments, subscriptions) on their real calendar dates; variable (materials, shipping, ads) estimated from the trailing 8–12 weeks of actuals.
  5. Compute the 13-week ladder with code. Week by week: opening + inflows − outflows = closing. Run three scenarios: committed-only, committed+likely, all-in. No mental math on real money.
  6. Find the low point. The minimum closing balance in the committed-only scenario, with its week and dates. That number — not the average — is the headline.
  7. Measure runway. Weeks until the committed-only closing crosses zero; report "13+" if it never does. Give the committed+likely runway for context.
  8. If runway < 8 weeks, pull three levers. Quantify each in weeks of runway bought:
    • Collect faster: name the invoices to chase today; propose deposits on new work.
    • Cut: the largest discretionary variable cost that dies without killing revenue.
    • Delay: which payable, and the exact ask to the vendor (split, +30 days, pause).
  9. Deliver the snapshot in the format below and date the next refresh — weekly if runway < 8, monthly otherwise.

Read the full file on GitHub · 75 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. 10d ago First seen · 75 lines · 0 tokens per session scan A c1e5963c5112

Subscribe to this mod's changes

cash-flow-snapshot is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,239 tokens. 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 2026-08-30.

Related

Other skills, from other repositories

mcp-lark

Based on FeiShu(飞书) / Lark's OpenAPI MCP server, manage user information, chats, emails, cloud documents, multidimensional tables, tasks, calendars, etc.

aahl/skills · 45 tokens

giasip-dispatch

A skill for sending a task to other AI models and collecting their results. It supports direct API calls, command-line tools and built-in internal agents, depending on the model.

GiaSip/giasip-skills · 162 tokens

knowing-and-doing-as-one

Activate when: user says 'I know I should but I haven't', a team is stuck in analysis paralysis going in circles, you need to assess whether someone actually learned from a past experience, a strategy or lessons-learned doc has produced no operational change, or an organization keeps repeating the same mistake. Do NOT…

deciqAI/knowledge-skills · 118 tokens

lifestage-value-curve

Activate when: someone asks 'what should I focus on at my age,' 'I feel like I'm wasting my best years,' 'how do I plan my career long-term,' 'what does my 40s/50s demand,' or a person is clearly investing for the wrong life stage (Heroic Age execution in the Golden Age, or Silver Age coasting in the Heroic Age). Do…

deciqAI/knowledge-skills · 130 tokens

checklist

Activate when: user says 'let's make sure we don't skip anything', 'we need a pre-flight', 'build me a checklist for X', 'we keep missing steps in our deployment / close / launch', 'Gawande / Pronovost / checklist manifesto'. Do NOT activate when: the task is simple and one-off with no recurrence; the user is asking…

deciqAI/knowledge-skills · 105 tokens

deep-work

Activate when: user says 'I can never find time for focused work', 'I feel busy but produce nothing', 'I keep getting interrupted', 'I want to protect my focus time', 'flow state', 'deliberate practice', 'Cal Newport', or asks how to make progress on hard cognitive work (research, writing, engineering, strategy). Do…

deciqAI/knowledge-skills · 123 tokens