cascadeflow

cascadeflow is a skill for Codex from lemony-ai/cascadeflow. It costs 49 tokens per session (1,334 once invoked), scanned A, original, MIT.

An OpenClaw model-routing service that sends requests through a small first model and uses a verifier when needed. It can assign models by domain, such as coding, web search, or reasoning, and supports OpenClaw events.

In plain words
What is it for?
Use it to configure OpenClaw model routing, streaming cascades, multi-step agent loops, health checks, chat calls, and optional usage statistics.
Why use it?
It helps choose different models for different tasks while using a verifier only when required, with the stated goal of reducing cost and response time.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: built for openclaw.

Good fit Use it to configure OpenClaw model routing, streaming cascades, multi-step agent loops…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lemony-ai/cascadeflow/cascadeflow-clawhub
About the project

cascadeflow is an in-process runtime for AI agents that makes model and execution decisions during agent loops, including model selection, budget checks, and stop, continue, or escalation actions. It is used to manage cost, latency, quality, policy, compliance, and energy across agent frameworks, while the catalogue skills integrate those decisions into supported agent workflows.

lemony-ai/cascadeflow · 3,964 stars · on GitHub · cascadeflow.ai

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 lemony-ai/cascadeflow --skill cascadeflow-clawhub
Clone the repo
git clone --depth 1 https://github.com/lemony-ai/cascadeflow

Made for: 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 cascadeflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/lemony-ai/cascadeflow/cascadeflow-clawhub.svg)](https://agentmods.dev/skills/lemony-ai/cascadeflow/cascadeflow-clawhub)
Your own site
<a href="https://agentmods.dev/skills/lemony-ai/cascadeflow/cascadeflow-clawhub"><img src="https://agentmods.dev/badge/skills/lemony-ai/cascadeflow/cascadeflow-clawhub.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,334 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 $0.00049 $0.01334
Opus 5 $0.00024 $0.00667
Sonnet 5 $0.00010 $0.00267
Haiku 4.5 $0.00005 $0.00133

Measured 7d ago against content hash e702015ea1b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

cascadeflow 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 7d 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.

examples/integrations/openclaw/cascadeflow-clawhub/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CascadeFlow: Cost + Latency Reduction | 17+ Domain-Aware Models + OpenClaw-Native Events

Use CascadeFlow as an OpenClaw provider to lower cost and latency via cascading. Assign up to 17 domain-specific models (for coding, web search, reasoning, and more), including OpenClaw-native event handling, and cascade between them (small model first, verifier when needed). Keep setup minimal, then verify with one health check and one chat call.

Why Use It

  • Reduce spend with drafter/verifier cascading.
  • Run 17+ domain-aware model assignments (code, reasoning, web-search, and more).
  • Support cascading with streaming and multi-step agent loops.
  • Handle OpenClaw-native event/domain signals for smarter model selection.

Security Defaults

  • Install from PyPI and verify package artifact before first run.
  • Keep the server bound to localhost by default.
  • Use explicit auth tokens for chat and stats endpoints (recommended for production).
  • Expose remote access only behind TLS/reverse proxy with strong tokens.
  • Use least-privilege provider keys (separate test keys from production keys).

How It Works

  1. OpenClaw sends requests to CascadeFlow through OpenAI-compatible /v1/chat/completions.
  2. CascadeFlow reads prompt context plus OpenClaw-native event/domain metadata (for example metadata.method, metadata.event, and channel/category hints).
  3. CascadeFlow selects a domain-aware drafter/verifier pair (small model first).
  4. If quality passes threshold, drafter answer is returned (cost/latency advantage).
  5. If quality fails threshold, verifier runs and final answer is upgraded.
  6. The same cascading behavior is supported for streaming and multi-step agent loops.

Advantages

  • Lower average cost by avoiding verifier calls when not needed.
  • Lower average latency for simple and medium tasks.
  • Better quality on hard tasks through verifier fallback.
  • Better operational handling through OpenClaw-native event/domain understanding.

Quick Start

Or ask your OpenClaw agent to set it up for you as an OpenClaw custom provider with OpenClaw-native events and domain understanding.

Read the full file on GitHub · 116 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 116 lines · 49 tokens per session scan A e702015ea1b6

Subscribe to this mod's changes

cascadeflow is a skill published in the GitHub repository lemony-ai/cascadeflow (3,964 stars, last pushed 10d ago), licensed MIT. It adds 49 tokens to every session and 1,334 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

git-memory-remember

Save one durable memory into Tau Git Memory.

AbdoKnbGit/tau · 0 tokens

git-memory-recall

You are retrieving facts from Tau Git Memory.

AbdoKnbGit/tau · 0 tokens

html-artifacts

Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.

langchain-ai/open-swe · 51 tokens

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.pdf

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…

aden-hive/hive · 98 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens