fundos-waterfall

fundos-waterfall is a skill for Claude Code, Codex from 8vdx1/fundos-mcp. It costs 112 tokens per session (1,926 once invoked), scanned A, original, MIT.

A guide for splitting private-fund distributions between investors and the manager under the fund agreement.

In plain words
What is it for?
It helps model European or American distribution waterfalls, calculate investor and manager shares, explain carry and hurdle results, and test how different exit values affect the split.
Why use it?
It accounts for terms that vary by fund, such as preferred returns, catch-up payments, carried interest, and clawbacks.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It helps model European or American distribution waterfalls, calculate investor and manager shares, explain carry and hurdle results, and test how different exit values affect the split.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/8vdx1/fundos-mcp/fundos-waterfall
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 8vdx1/fundos-mcp --skill fundos-waterfall
Clone the repo
git clone --depth 1 https://github.com/8vdx1/fundos-mcp

Made for: Claude Code, Codex.

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 fundos-waterfall

README.md
[![agentmods](https://agentmods.dev/badge/skills/8vdx1/fundos-mcp/fundos-waterfall/github.svg)](https://agentmods.dev/skills/8vdx1/fundos-mcp/fundos-waterfall)
Your own site
<a href="https://agentmods.dev/skills/8vdx1/fundos-mcp/fundos-waterfall"><img src="https://agentmods.dev/badge/skills/8vdx1/fundos-mcp/fundos-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 fundos-waterfall

Your own site · 80×15
<a href="https://agentmods.dev/skills/8vdx1/fundos-mcp/fundos-waterfall"><img src="https://agentmods.dev/badge/skills/8vdx1/fundos-mcp/fundos-waterfall.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,926 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 $0.00112 $0.01926
Opus 5 $0.00056 $0.00963
Sonnet 5 $0.00022 $0.00385
Haiku 4.5 $0.00011 $0.00193

Measured 11d ago against content hash 402922efd740, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

fundos-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 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.

integrations/qm/skills/fundos-waterfall/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Waterfall Calculations

The LPA controls, not convention. Every default in this document is a market norm that some fund's LPA overrides. Preferred return rate and compounding, catch-up structure, carry basis, fee offsets, recycling — all of it varies. When you don't know the fund's actual terms, say so and state the assumption you used rather than presenting a market default as the answer.

Let FundOS compute it

FundOS implements the fund's own waterfall conventions. Your arithmetic will drift from the books; theirs is what the LP sees on a statement. Compute through the API and use the hand math below to explain the result, not to replace it.

fundos GET  /fundos/cfo/accounts        # fund vehicles, commitments, capital structure
fundos GET  /fundos/investors/lp        # LP contributions — pref accrues per contribution
fundos POST /fundos/cfo/waterfall '{"distributable": 85000000, "committed": 40000000, "hurdle_pct": 8, "carry_pct": 20}'

Field names matter here and are not the ones you would guess:

Field Notes
distributable The proceeds being split. Not proceeds.
committed Required, must be > 0. Omitting it returns 400 committed must be positive.
hurdle_pct Default 0.08. Accepts either form — 8 and 0.08 both mean 8%.
carry_pct Default 0.20. Same dual form.
catchup_pct Default 1.0 (full catch-up). Fraction only, 0–1.

There is no fund_account_id on this endpoint — it is a stateless calculator, so pull the fund's real committed from /fundos/cfo/accounts and pass it in.

The result (under .data) gives lp_total, gp_total, total_distributed, and a tiers array with label / distributed / lp_amount / gp_amount per tier. Worked example — 85M distributable on 40M committed at 8% / 20% returns LP 76,000,000 and GP 9,000,000 across four tiers (return of capital 40M, preferred return 3.2M, GP catch-up 0.8M, carry split 41M).

For a single asset's IRR / MOIC / WAL feeding into a scenario:

Read the full file on GitHub · 169 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 · 169 lines · 112 tokens per session scan A 402922efd740

Subscribe to this mod's changes

fundos-waterfall is a skill published in the GitHub repository 8vdx1/fundos-mcp (1 stars, last pushed 27d ago), licensed MIT. It adds 112 tokens to every session and 1,926 once invoked, about $0.0006 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.