OpenClaw is an AI assistant that runs on a user's own devices and connects to chat services such as Discord, Slack, Telegram, and WhatsApp. Individuals or teams use it for assistant tasks while keeping its state, memory, and credentials on their hardware and choosing the models or agent harnesses it uses. The catalogue entries are skills, agents, instructions, hooks, and settings that define or extend OpenClaw's workflow.
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.
npx skills add openclaw/openclaw --skill node-connectgit clone --depth 1 https://github.com/openclaw/openclawWrote 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.
[](https://agentmods.dev/skills/openclaw/openclaw/node-connect)<a href="https://agentmods.dev/skills/openclaw/openclaw/node-connect"><img src="https://agentmods.dev/badge/skills/openclaw/openclaw/node-connect/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.
<a href="https://agentmods.dev/skills/openclaw/openclaw/node-connect"><img src="https://agentmods.dev/badge/skills/openclaw/openclaw/node-connect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 102 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.01484 |
| Opus 5.5 | $0.00016 | $0.00594 |
| Sonnet 5.5 | $0.00008 | $0.00297 |
| Haiku 4.5 | $0.00004 | $0.00148 |
Grade A, and why
node-connect 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.
How it starts
The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Node Connect
Goal: fix one exact client against one exact Gateway, then prove that client's fresh connection.
1. Lock the target
Record the target environment/profile, OpenClaw binary, config/state root, Gateway URL/port, and service before changing anything.
- Use the named deployment wrapper/profile for every config, log, service, device, and node command.
- Never drift to a bare
openclaw, proof environment, or similarly named deployment. - If the global executable is stale, invoke the target through its owner.
- Verify status, config, logs, and process identity describe the same Gateway.
Identify the target Gateway before changing pairing or auth.
2. Classify the client
Classify from the request and Gateway log before choosing commands:
- Control UI browser: the user says browser, dashboard, Control UI, or webchat; logs show
client=openclaw-control-uiormode=webchat. - Native mobile/node: the official app shows Connect, Scan QR, or setup code; logs/request metadata show a native client or
role=node.
A phone can be either client. Do not use openclaw qr or openclaw nodes status for a phone browser; those belong to native mobile/node pairing.
3. Observe the failing attempt
Run these through the locked target:
openclaw gateway status --deep
openclaw logs --follow --json
openclaw devices list
openclaw config get gateway.mode
openclaw config get gateway.bind
openclaw config get gateway.remote.url
openclaw config get gateway.auth.mode
openclaw config get gateway.auth.allowTailscale
openclaw config get gateway.tailscale.mode
Have the client retry once while logs are live. Correlate its client ID, mode, platform, address, auth result, device ID, user, and close code. Ignore other paired devices.
Interpret the first failed transition:
- No matching Gateway attempt: route, DNS, TLS, origin, or proxy problem.
token_missing,password_missing, mismatch, or Tailscale identity failure: auth failed before pairing, so an empty pending list is expected.pairing required: route and auth succeeded; approve the exact pending request.client connected: matchconn,client,mode, androleto the exact client. Admission precedes the hello response; if followed by1006, preserve auth/pairing and inspect hello delivery, lifecycle, transport, proxy, or reconnect. Older builds use overlappingauthenticated user connected/webchat connectedrecords that omit ephemeral clients.1006without a matching application-level admission record does not prove auth/pairing; inspect the earlier handshake transition.
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.
- 7d ago Changed 40f47cc3c692
- 29d ago Changed 334c20d39732
- 1mo ago First seen · 124 lines · 39 tokens per session scan A f5cb8259f13b
node-connect is a skill published in the GitHub repository openclaw/openclaw (392,886 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 1,484 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
error-recovery-skill
Handle errors gracefully with retry strategies and fallback patterns.
location-skill
Get Android device GPS location - latitude, longitude, accuracy, speed, and provider information.
wifi-skill
Control Android WiFi - enable, disable, get status, scan for networks, and get current connection info.
app-launcher-skill
Launch Android applications by package name. Open any installed app programmatically.
app-list-skill
Get list of installed Android applications with package names, versions, and metadata.
audio-skill
Control Android audio - get/set volume, mute/unmute for media, ringtone, notification, and call volumes.