waterfall

waterfall is a command for Claude Code from Aznatkoiny/zAI-Skills. It costs 17 tokens per session (1,108 once invoked), scanned A, original, MIT.

A calculator for splitting profits in a real estate syndication, where general partners and limited partners share returns according to investment hurdles.

In plain words
What is it for?
It helps calculate tiered distributions using preferred returns, IRR hurdles, catch-up rules, and different whole-fund or deal-by-deal structures.
Why use it?
It helps model how changing return thresholds and profit splits affect each investor group.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the real-estate-investment plugin — 1 skill, 9 commands, 4 agents shipped together

Good fit It helps calculate tiered distributions using preferred returns, IRR hurdles, catch-up rules, and different whole-fund or deal-by-deal structures.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Aznatkoiny/zAI-Skills
Claude Code
/plugin install real-estate-investment

Made for: Claude Code.

Or install real-estate-investment, the plugin that ships this one along with the rest of its 1 skill, 9 commands, 4 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 waterfall

README.md
[![agentmods](https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/waterfall/github.svg)](https://agentmods.dev/commands/aznatkoiny/zai-skills/waterfall)
Your own site
<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/waterfall"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/waterfall/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 waterfall

Your own site · 80×15
<a href="https://agentmods.dev/commands/aznatkoiny/zai-skills/waterfall"><img src="https://agentmods.dev/badge/commands/aznatkoiny/zai-skills/waterfall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,108 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 $0.00017 $0.01108
Opus 5 $0.00009 $0.00554
Sonnet 5 $0.00003 $0.00222
Haiku 4.5 $0.00002 $0.00111

Measured 8d ago against content hash 0b8e60267e56, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

waterfall 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.

real-estate-investment/commands/waterfall.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Syndication Waterfall Calculator

Requested waterfall type (may be empty): $ARGUMENTS

Instructions

When this command is invoked, model a real estate syndication waterfall by running the plugin's tested script — do not re-write the tier math from prose:

1. Load Reference Material

Read ${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/references/advanced-analysis.md (§3 Waterfall Distribution Modeling) for tier structures, catch-up mechanics, American vs. European differences, and the script's documented assumptions.

2. Collect Syndication Structure

Use AskUserQuestion to gather:

Equity Structure:

  • LP equity contribution (typically 90-95% of total)
  • GP equity co-investment (dollar amount or %; may be zero)

Hurdles and Splits:

  • Preferred return rate (annual %, typical: 6-8%) — in the script this is the first IRR hurdle (compound, cumulative)
  • IRR hurdle schedule and LP share per tier, e.g. 100% LP to 8%, 80/20 to 12%, 70/30 to 18%, 60/40 above (the script's defaults)
  • Residual LP split above the highest hurdle

Waterfall Type (skip if provided via $ARGUMENTS):

  • European (whole-fund): hurdles measured on aggregate dated cash flows — this is what the script implements directly
  • American (deal-by-deal): run the script once per deal, each with its own equity and cash flow vector, then sum GP promote across deals

3. Collect Cash Flow Projections

Ask for the annual distributable cash flows (end-of-year, Years 1-N), including exit proceeds in the final year. Alternatively, derive them from a hold period + target equity multiple + distribution pattern (e.g., "all at exit" or "X% annually plus exit"). If a pro forma was already built with /pro-forma, reuse its net cash flows and sale proceeds.

4. Run the Canonical Script

The tested implementation is ${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/scripts/waterfall.py. Write the structure into waterfall_inputs.json and run via Bash:

# Schema template:
python "${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/scripts/waterfall.py" --sample-input

# After writing waterfall_inputs.json (lp_capital, gp_capital,
# annual_cash_flows, hurdles, lp_splits, residual_lp_split):
python "${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/scripts/waterfall.py" \
    --input waterfall_inputs.json --output waterfall_results.json
python "${CLAUDE_PLUGIN_ROOT}/skills/real-estate-investment/scripts/waterfall.py" \
    --input waterfall_inputs.json --table

Read the full file on GitHub · 95 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 · 95 lines · 17 tokens per session scan A 0b8e60267e56

Subscribe to this mod's changes

waterfall is a command published in the GitHub repository Aznatkoiny/zAI-Skills (9 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 1,108 once invoked, about $0.0001 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.