# Send cascadeflow: Cost + Latency Reduction to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "cascadeflow",
    "name": "cascadeflow: Cost + Latency Reduction",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/saschabuehrle/cascadeflow",
    "canonicalUrl": "https://clawhub.ai/saschabuehrle/cascadeflow",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/cascadeflow",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cascadeflow",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "agents/openai.yaml",
      "references/clawhub_publish_pack.md",
      "references/market_positioning.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "cascadeflow",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T17:38:38.346Z",
      "expiresAt": "2026-05-11T17:38:38.346Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cascadeflow",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=cascadeflow",
        "contentDisposition": "attachment; filename=\"cascadeflow-1.1.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "cascadeflow"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/cascadeflow"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/cascadeflow",
    "downloadUrl": "https://openagent3.xyz/downloads/cascadeflow",
    "agentUrl": "https://openagent3.xyz/skills/cascadeflow/agent",
    "manifestUrl": "https://openagent3.xyz/skills/cascadeflow/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/cascadeflow/agent.md"
  }
}
```
## Documentation

### 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

OpenClaw sends requests to CascadeFlow through OpenAI-compatible /v1/chat/completions.
CascadeFlow reads prompt context plus OpenClaw-native event/domain metadata (for example metadata.method, metadata.event, and channel/category hints).
CascadeFlow selects a domain-aware drafter/verifier pair (small model first).
If quality passes threshold, drafter answer is returned (cost/latency advantage).
If quality fails threshold, verifier runs and final answer is upgraded.
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.

Install and verify package source:

python3 -m venv .venv
source .venv/bin/activate
python -m pip install --upgrade "cascadeflow[openclaw]>=0.7,<0.8"
python -m pip show cascadeflow
python -m pip download --no-deps "cascadeflow[openclaw]>=0.7,<0.8" -d /tmp/cascadeflow_pkg
python -m pip hash /tmp/cascadeflow_pkg/cascadeflow-*.whl

Optional variants:

python -m pip install --upgrade "cascadeflow[openclaw,anthropic]>=0.7,<0.8"   # Anthropic-only preset
python -m pip install --upgrade "cascadeflow[openclaw,openai]>=0.7,<0.8"      # OpenAI-only preset
python -m pip install --upgrade "cascadeflow[openclaw,providers]>=0.7,<0.8"   # Mixed preset

Pick preset + credentials:

Presets: examples/configs/anthropic-only.yaml, examples/configs/openai-only.yaml, examples/configs/mixed-anthropic-openai.yaml
Provider key(s): ANTHROPIC_API_KEY=... and/or OPENAI_API_KEY=... (required based on selected preset)
Service tokens: --auth-token ... and --stats-auth-token ... (recommended for production; use long random values)

Start server (safe local default):

set -a; source .env; set +a
python3 -m cascadeflow.integrations.openclaw.openai_server \\
  --host 127.0.0.1 --port 8084 \\
  --config examples/configs/anthropic-only.yaml \\
  --auth-token local-openclaw-token \\
  --stats-auth-token local-stats-token

Optional harness activation (runtime in-loop policy controls):

# Observe first (recommended): log decisions, no blocking
python3 -m cascadeflow.integrations.openclaw.openai_server \\
  --host 127.0.0.1 --port 8084 \\
  --config examples/configs/anthropic-only.yaml \\
  --harness-mode observe

# Enforce mode with limits
python3 -m cascadeflow.integrations.openclaw.openai_server \\
  --host 127.0.0.1 --port 8084 \\
  --config examples/configs/anthropic-only.yaml \\
  --harness-mode enforce \\
  --harness-budget 1.0 \\
  --harness-max-tool-calls 12 \\
  --harness-max-latency-ms 3500 \\
  --harness-compliance strict

Configure OpenClaw provider:

baseUrl: http://<cascadeflow-host>:8084/v1 (local default: http://127.0.0.1:8084/v1)
If remote: http://<server-ip>:8084/v1 or https://<domain>/v1 (TLS/reverse proxy)
api: openai-completions
model: cascadeflow
apiKey: same value as your --auth-token

### Commands

/model cflow: default OpenClaw model switch using alias cflow.
/cascade: optional custom command (if configured in OpenClaw).
/cascade savings: optional custom subcommand for cost stats.
/cascade health: optional custom subcommand for service status.

### Links

Full setup + configs: references/clawhub_publish_pack.md
Listing strategy: references/market_positioning.md
Official docs: https://github.com/lemony-ai/cascadeflow/blob/main/docs/guides/openclaw_provider.md
GitHub repository: https://github.com/lemony-ai/cascadeflow
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: saschabuehrle
- Version: 1.1.1
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-04T17:38:38.346Z
- Expires at: 2026-05-11T17:38:38.346Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/cascadeflow)
- [Send to Agent page](https://openagent3.xyz/skills/cascadeflow/agent)
- [JSON manifest](https://openagent3.xyz/skills/cascadeflow/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/cascadeflow/agent.md)
- [Download page](https://openagent3.xyz/downloads/cascadeflow)