Skip to content
Agentmart
Submit a tool

openclaw-gateway

OpenClaw gateway operations and HTTP/API surface.

Skill by Hashi-Ai-Dev

IndexedMIT★ 6
Write a review

Chalk Labs

Need help deploying openclaw-gateway?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/hashi-ai-dev-openclaw-gateway

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

OpenClaw gateway operations and HTTP/API surface. Use when configuring gateway runtime, the OpenAI-compatible HTTP API, OpenResponses API, observability (OpenTelemetry, Prometheus), secrets, sandbox vs tool policy vs elevated, security audit, gateway troubleshooting, gateway exposure (Tailscale/runbook), or gateway-owned node pairing for iOS / remote nodes (Option B). Triggers on: gateway, gateway config, configuration, HTTP API, OpenAI compatible, OpenResponses, telemetry, OpenTelemetry, prometheus, metrics, secrets, secret resolution, sandbox, tool policy, elevated, security audit, security-audit-checks, exposure, Tailscale, runbook, doctor, diagnostic, CLI backends, config-agents, config-channels, config-tools, pairing, gateway-owned, gateway owned, gatewayowned, node pairing, node pairing flow, pairing option, pairing approval.

Use cases: backend, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/openclaw-gateway

What's inside

Skill name
openclaw-gateway
Description
OpenClaw gateway operations and HTTP/API surface. Use when configuring gateway runtime, the OpenAI-compatible HTTP API, OpenResponses API, observability (OpenTelemetry, Prometheus), secrets, sandbox vs tool policy vs elevated, security audit, gateway troubleshooting, gateway exposure (Tailscale/runbook), or gateway-owned node pairing for iOS / remote nodes (Option B). Triggers on: gateway, gateway config, configuration, HTTP API, OpenAI compatible, OpenResponses, telemetry, OpenTelemetry, prometheus, metrics, secrets, secret resolution, sandbox, tool policy, elevated, security audit, security-audit-checks, exposure, Tailscale, runbook, doctor, diagnostic, CLI backends, config-agents, config-channels, config-tools, pairing, gateway-owned, gateway owned, gatewayowned, node pairing, node pairing flow, pairing option, pairing approval.
License
MIT
Instructions
42 lines in SKILL.md · view on GitHub

Files (27)

  • SKILL.md
  • authentication.md · references/
  • bonjour.md · references/
  • cli-backends.md · references/
  • config-agents.md · references/
  • config-channels.md · references/
  • config-tools.md · references/
  • configuration-examples.md · references/
  • configuration-reference.md · references/
  • configuration.md · references/
  • discovery.md · references/
  • doctor.md · references/
  • exposure-runbook.md · references/
  • health.md · references/
  • openai-http-api.md · references/
  • openresponses-http-api.md · references/
  • openshell.md · references/
  • opentelemetry.md · references/
  • pairing.md · references/
  • prometheus.md · references/
  • protocol.md · references/
  • sandbox-vs-tool-policy-vs-elevated.md · references/
  • secrets.md · references/
  • security-audit-checks.md · references/
  • security.md · references/
  • audit-checks.md · references/security/
  • troubleshooting.md · references/

SKILL.md (first lines)

# OpenClaw Gateway

The gateway is the long-running process that owns the HTTP API surface, agent routing, and observability. This skill covers gateway-specific configuration, the protocol/HTTP layer, telemetry, secrets, sandboxing, and operational runbooks.

> **Note:** For schema-level reference of every config key, see `openclaw-config`. This skill focuses on gateway **operational** concerns.

## What this skill covers

- **HTTP / API surface** — OpenAI-compatible API, OpenResponses API, internal protocol
- **Telemetry** — OpenTelemetry, Prometheus metrics
- **Secrets** — secret resolution, SecretRef credential surface
- **Sandboxing** — sandbox vs tool-policy vs elevated distinction
- **Operational runbooks** — exposure (Tailscale), security audit, gateway troubleshooting, doctor
- **Per-area gateway config** — agents, channels, tools (sub-pages of the gateway config tree)

## References

- `references/openai-http-api.md` — OpenAI-compatible HTTP API surface
- `references/openresponses-http-api.md` — OpenResponses HTTP API
- `references/protocol.md` — internal gateway protocol
- `references/opentelemetry.md` — OpenTelemetry instrumentation
- `references/prometheus.md` — Prometheus metrics endpoint
- `references/secrets.md` — secret resolution, SecretRef credential surface
- `references/sandbox-vs-tool-policy-vs-elevated.md` — sandboxing vs tool policy vs elevated
- `references/security-audit-checks.md` — security audit runbook
- `references/security/audit-checks.md` — granular audit-check reference
- `references/security.md` — gateway security overview
- `references/exposure-runbook.md` — gateway exposure (Tailscale) runbook
- `references/health.md` — gateway health endpoints
- `references/troubleshooting.md` — gateway troubleshooting
- `references/doctor.md` — `openclaw doctor` integration
- `references/cli-backends.md` — CLI backends integration
- `references/configuration.md` — gateway configuration overview
- `references/configuration-reference.md` — full configuration key reference
- `references/configuration-examples.md` — example gateway configuration snippets
- `references/authentication.md` — gateway authentication
- `references/config-agents.md` — gateway config: agents subtree
- `references/config-channels.md` — gateway config: channels subtree
- `references/config-tools.md` — gateway config: tools subtree
- `references/pairing.md` — gateway pairing flow

From Hashi-Ai-Dev/openclaw-clawdoc, MIT.

Signals

Stars
6
Forks
0
Open issues
0
Last commit (this folder)
Jul 1, 2026 (4 months ago)
Last release
Jul 6, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Hashi-Ai-Dev

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get openclaw-gateway running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying openclaw-gateway?

CallGet help
Cite this page

openclaw-gateway skill. Agent Mart. https://agentmart.dev/skills/hashi-ai-dev-openclaw-gateway (last updated 2026-10-24)