agentCLAWHUBUnverified
mx-auto
Local Runtime automation entrypoint for App triggers, read-only browser sandbox inspection, and local script execution. Use when the user wants to list or ru... Skill: mx-auto Owner: yiming1001 Summary: Local Runtime automation entrypoint for App triggers, read-only browser sandbox inspection, and local script execution. Use when the user wants to list or ru... Tags: latest:1.0.4 Version history: v1.0.4 | 2026-05-19T10:46:39.784Z | user Add progressive references plus sandbox tabs/snapshot and local script list/show/run routing. v1.0.3 | 2026-05-19T03:08:41.322Z | user Persi
OpenClaw
Rank
62
Safety
84
Downloads
964
Updated
Oct 12, 2026
Version
1.0.4
Source
CLAWHUB
About
What it does, and when to use it.
Capability contract not published. No trust telemetry is available yet. 964 downloads reported by the source. Last updated 10/12/2026.
Avoid when
- Contract metadata is missing or unavailable for deterministic execution.
Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing
Public facts
Every fact links back to the source it came from.
- Vendor
- Clawhubvendor · observed Oct 12, 2026
- Protocol compatibility
- OpenClawcompatibility · observed Oct 12, 2026
- Adoption signal
- 964 downloadsadoption · observed Oct 12, 2026
- Latest release
- 1.0.4release · observed May 19, 2026
- Handshake status
- UNKNOWNsecurity
What changed
Newest first. Only changes that point at a source are listed.
Release 1.0.4release
Add progressive references plus sandbox tabs/snapshot and local script list/show/run routing.
Observed May 19, 2026 · source
Install and run
Setup complexity: low.
clawhub skill install s17973ckq18hmgn6fyfhwykv1583h5nd:mx-auto- Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
- Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Contract: missing
curl -s "https://www.xpersona.co/api/v1/agents/clawhub-yiming1001-mx-auto/snapshot"
Run-check
$0.02 USD1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.
Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.
Documentation
CLAWHUB
55,304 characters of source documentation, loaded on request.
Extracted files
5 files captured from the source.
SKILL.md
---
name: mx-auto
description: Local Runtime automation entrypoint for App triggers, read-only browser sandbox inspection, and local script execution. Use when the user wants to list or run Runtime triggers, inspect existing browser sandbox tabs/snapshots, or list/show/run local App scripts.
---
# mx-auto
Use this skill as a lightweight router for local Runtime automation.
## Capabilities
- **Triggers**: list and run callable App triggers.
- Read [references/triggers.md](references/triggers.md) when the user asks to list, refresh, inspect, or run triggers.
- **Sandbox**: list existing browser sandbox tabs or snapshot an existing tab.
- Read [references/sandbox.md](references/sandbox.md) when the user asks about browser sandbox tabs, target IDs, snapshots, dashboard text, or URL-matched tab inspection.
- **Scripts**: list, show, or run local scripts/examples.
- Read [references/scripts.md](references/scripts.md) when the user asks to list scripts, inspect a script schema, or run a script directly.
- For complex mixed requests, read [references/learning-guide.md](references/learning-guide.md).
## Shared Runtime Defaults
Preferences file:
`$OPENCLAW_STATE_DIR/skill-state/mx-auto/preferences.json`
Fallback:
`$HOME/.openclaw/skill-state/mx-auto/preferences.json`
Helper:
```bash
bash {baseDir}/scripts/export_preference.sh show
bash {baseDir}/scripts/export_preference.sh apply-recommended
bash {baseDir}/scripts/export_preference.sh set-key defaultAppHome "/Users/zhym/Library/Application Support/rpa-app-executor"
```
Runtime base URL discovery:
1. `MX_APP_RUNTIME_BASE_URL`
2. `RPA_RUNTIME_BASE_URL`
3. stored `defaultLocalBaseUrl`
4. standard Runtime ports: `8877`, `8878`, `8879`
Runtime app home discovery:
1. `--app-home`
2. `MX_AUTO_APP_HOME`
3. `RPA_APP_HOME`
4. stored `defaultAppHome`
5. platform default app home
Runtime admin token discovery:
1. `MX_APP_RUNTIME_ADMIN_TOKEN`
2. `RPA_RUNTIME_ADMIN_TOKEN`
3. `{resolved app home}/runtime/admin-token.json`
Never store or print the Runtime admin token value. App updates may rotate or recreate it; re-read the token file at runtime.
## Entry Points
Prefer the wrapper:
```bash
bash {baseDir}/scripts/run.sh ...
```
Triggers:
```bash
bash {baseDir}/scripts/run.sh triggers list --format json
bash {baseDir}/scripts/run.sh triggers run --trigger-name "小红书测试"
```
Sandbox:
```bash
bash {baseDir}/scripts/run.sh sandbox tabs --format json
bash {baseDir}/scripts/run.sh sandbox snapshot --url-contains dashboardV4 --url-not-contains /review
```
Scripts:
```bash
bash {baseDir}/scripts/run.sh scripts list --format json
bash {baseDir}/scripts/run.sh scripts show xiaohongshu.note.search.v1.json --format json
bash {baseDir}/scripts/run.sh scripts run xiaohongshu.note.search.v1.json --input-json '{"keyword":"美食探店"}' --wait true --format json
```
Legacy trigger commands remain supported:
```bash
bash {baseDir}/scripts/run.sh --list-triggers
bash {baseDir}/scripts/run.sh --trigger-name "小红书测试"
_meta.json
{
"ownerId": "kn7e8rp9zay3je2bycn9zrmztx82hy57",
"slug": "mx-auto",
"version": "1.0.4",
"publishedAt": 1779187599784
}references/learning-guide.md
# mx-auto Learning Guide Use this guide only for complex requests that combine trigger, sandbox, or script operations. ## Routing - Trigger list/run requests: read `references/triggers.md`. - Existing browser sandbox tab/snapshot requests: read `references/sandbox.md`. - Local script list/show/run requests: read `references/scripts.md`. ## Shared Rules - Prefer auto-discovery before asking for Runtime URL, app home, or token. - Store app home and other non-secret defaults only. - Never store, print, or copy the Runtime admin token value. - Use exact names for execution targets; do not fuzzy-match a trigger or script when running it. - Ask only after Runtime discovery or target resolution fails. ## Failure Framing Clearly distinguish: - Runtime unavailable - Runtime unauthorized or token file missing - target resolution/cache miss - command execution failure - sandbox no-match or multiple-match disambiguation
references/sandbox.md
# Sandbox Workflow
Use this reference when inspecting existing browser sandbox tabs or snapshotting an existing tab.
## Rules
- Strictly read-only.
- Only list tabs or snapshot an existing target.
- Do not navigate.
- Do not create pages or tabs.
- Do not click, type, or mutate browser state.
## Commands
```bash
bash {baseDir}/scripts/run.sh sandbox tabs
bash {baseDir}/scripts/run.sh sandbox tabs --profile browser-1 --format json
bash {baseDir}/scripts/run.sh sandbox snapshot --target-id <targetId>
bash {baseDir}/scripts/run.sh sandbox snapshot --url-contains dashboardV4 --url-not-contains /review
```
## Runtime API
Call `POST /browser` with Runtime admin auth.
Tabs:
```json
{ "action": "tabs", "profile": "browser-1" }
```
Snapshot:
```json
{
"action": "snapshot",
"profile": "browser-1",
"targetId": "<targetId>",
"maxChars": 6000
}
```
## Target Resolution
- `--target-id` wins when present.
- Otherwise filter existing tabs by all `--url-contains` values and no `--url-not-contains` values.
- Zero matches is a clear no-match error.
- Multiple matches requires user disambiguation.
## Output
- Tabs: profile, tab count, targetId, title, URL.
- Snapshot: profile, targetId, matched URL, text snapshot or extracted content.references/scripts.md
# Scripts Workflow
Use this reference when listing, showing, or running local App scripts/examples.
## Commands
```bash
bash {baseDir}/scripts/run.sh scripts list
bash {baseDir}/scripts/run.sh scripts list --format json
bash {baseDir}/scripts/run.sh scripts show xiaohongshu.note.search.v1.json --format json
bash {baseDir}/scripts/run.sh scripts run xiaohongshu.note.search.v1.json --input-json '{"keyword":"美食探店"}' --wait true --format json
```
## Runtime API
- List/show scripts from `GET /examples/catalog`.
- Run scripts through `POST /local/commands/send` with `target: "script.run"`.
Run body:
```json
{
"target": "script.run",
"payload": {
"name": "xiaohongshu.note.search.v1.json",
"inputOverrides": {}
},
"wait": true,
"leaseTtlMs": 60000
}
```
## Resolution
- Run only exact script `name` matches.
- Do not fuzzy-match script names for execution.
- If no exact match exists, list candidate names from the current catalog.
## Input
- `--input-json` must be a JSON object.
- Pass it as `inputOverrides`.
- Do not invent required fields.
- If Runtime or script reports missing input, surface the error clearly.
## Output
- List: script count, name, platform label, runner.
- Show: manifest metadata and input schema.
- Run: preserve `target`, `commandId`, `resultType`, `status`, and message.Github ReposUpdated 3d agoRank 70
AionUi
Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!
MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70
activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
OPENCLAW
Github ReposUpdated 6mo agoRank 70
cherry-studio
AI productivity studio with smart chat, autonomous agents, and 300+ assistants.
MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70
CopilotKit
The Frontend for Agents & Generative UI. React + Angular
OPENCLAW
Machine-readable data
The same record, as JSON, for agents and crawlers.
- Card JSON
- Facts JSON
- Snapshot JSON
- Contract JSON
- Trust JSON
- Changes JSON
- Warnings JSON
- Seen by JSON
- Disagreements JSON
{
"facts": [
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Clawhub",
"href": "https://clawhub.ai/yiming1001/skills/mx-auto",
"sourceUrl": "https://clawhub.ai/yiming1001/skills/mx-auto",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-12T00:58:53.874Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "OpenClaw",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-yiming1001-mx-auto/contract",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-yiming1001-mx-auto/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-10-12T00:58:53.874Z",
"isPublic": true
},
{
"factKey": "traction",
"category": "adoption",
"label": "Adoption signal",
"value": "964 downloads",
"href": "https://clawhub.ai/yiming1001/mx-auto",
"sourceUrl": "https://clawhub.ai/yiming1001/mx-auto",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-10-12T00:58:53.874Z",
"isPublic": true
},
{
"factKey": "latest_release",
"category": "release",
"label": "Latest release",
"value": "1.0.4",
"href": "https://clawhub.ai/yiming1001/mx-auto",
"sourceUrl": "https://clawhub.ai/yiming1001/mx-auto",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-19T10:46:39.784Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://www.xpersona.co/api/v1/agents/clawhub-yiming1001-mx-auto/trust",
"sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-yiming1001-mx-auto/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
],
"events": [
{
"eventType": "release",
"title": "Release 1.0.4",
"description": "Add progressive references plus sandbox tabs/snapshot and local script list/show/run routing.",
"href": "https://clawhub.ai/yiming1001/mx-auto",
"sourceUrl": "https://clawhub.ai/yiming1001/mx-auto",
"sourceType": "release",
"confidence": "medium",
"observedAt": "2026-05-19T10:46:39.784Z",
"isPublic": true
}
]
}Record generated Oct 12, 2026.
For crawlers
This page is free to read. The run-check above is the only paid part, and it answers HTTP 402 until it is paid. Everything else here is public.
- One record, as JSON: card, facts, snapshot, contract, trust, changes, warnings, seen by, disagreements.
- Every agent, one feed: /.well-known/ai-catalog.json
- What this site sells, and the price: /.well-known/x402
- Paid run-check: /api/v1/agents/clawhub-yiming1001-mx-auto/run-check