gateway-safety
Safely update OpenClaw gateway configuration (openclaw.json) with automatic validation, backup, and 30-second health-check rollback. Use this skill whenever an agent needs to modify gateway settings, ports, provider credentials, or network bindings to ensure the session is not permanently lost due to a bad configuration.
Best use case
gateway-safety is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Safely update OpenClaw gateway configuration (openclaw.json) with automatic validation, backup, and 30-second health-check rollback. Use this skill whenever an agent needs to modify gateway settings, ports, provider credentials, or network bindings to ensure the session is not permanently lost due to a bad configuration.
Teams using gateway-safety should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/gateway-safety/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How gateway-safety Compares
| Feature / Agent | gateway-safety | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Safely update OpenClaw gateway configuration (openclaw.json) with automatic validation, backup, and 30-second health-check rollback. Use this skill whenever an agent needs to modify gateway settings, ports, provider credentials, or network bindings to ensure the session is not permanently lost due to a bad configuration.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agent for Product Research
Browse AI agent skills for product research, competitive analysis, customer discovery, and structured product decision support.
SKILL.md Source
# Gateway Safety This skill ensures that any modifications to the OpenClaw gateway configuration are done safely. It prevents "death loops" and permanent session loss by verifying the gateway can successfully reboot before committing to a new config. ## Core Rules 1. **Mandatory Script Use**: Never edit `~/.openclaw/openclaw.json` directly. Always use the provided `safe-gateway-update.sh` script. 2. **Anti-Loop Policy**: If the script fails 3 times consecutively, it will create a `GATEWAY_LOCKOUT` file. If this file exists, **STOP ALL OPERATIONS** and wait for Kevin. Do not attempt to bypass the lockout. 3. **Backup Awareness**: The script maintains its own backups, but for critical changes, manually verify `~/.openclaw/openclaw.json.known-good` is up to date. ## Usage To update the gateway configuration: 1. Prepare the new configuration JSON file (e.g., at `/tmp/new_config.json`). 2. Execute the safety script: ```bash [SKILL_PATH]/scripts/safe-gateway-update.sh /tmp/new_config.json [timeout_seconds] ``` 3. The script will: - Validate the JSON syntax. - Backup the current config. - Apply the new config and restart the gateway. - Poll for a successful "RPC probe: ok" status. - Roll back to the previous config if the health check fails or times out. ## Authorship Created by Kevin Smith & Rook (Orbit Smith), March 2026.
Related Skills
Food Safety & HACCP Compliance Agent
You are a food safety compliance specialist. Help businesses build, audit, and maintain HACCP plans and FDA/USDA food safety programs.
AI Safety Audit
Comprehensive AI safety and alignment audit framework for businesses deploying AI agents. Built around the UK AI Security Institute Alignment Project standards (2026), EU AI Act requirements, and NIST AI RMF.
Authensor Gateway
Fail-safe policy gate for OpenClaw marketplace skills. Intercepts tool calls before execution and checks them against your Authensor policy. Low-risk actions run automatically. High-risk actions require your approval. Dangerous actions are blocked. Only action metadata is sent to the control plane — never your files, API keys, or conversation content.
aimlapi-safety
Content moderation and safety checks. Instantly classify text or images as safe or unsafe using AI guardrails.
windows-healing-gateway
OpenClaw Gateway Self-Healing System for Windows
scar-safety
Agent safety that learns from incidents. Reflex arc blocks repeat threats without LLM calls.
crebee-social-media-gateway
CreBee 社交媒体网关。当用户需要管理社交媒体账号、发布内容（视频/图文/文章）、获取数据分析、访问粉丝画像、搜索话题/活动/音乐、或与抖音、B站、小红书、快手等 12 个平台交互时触发此技能。适用于 AI Agent 自动化管理中国社交媒体平台运营。 触发场景： - 发布内容到社交媒体平台 - 获取账号列表或账号信息 - 查询分析数据、数据概览、表现指标 - 访问粉丝/观众画像 - 搜索话题、标签、音乐、活动 - 管理抖音、B站、小红书、快手等平台的内容
SKILL.md - Gateway Watchdog Skill
> 一句话让 OpenClaw 安装 Gateway Watchdog
SKILL.md - OpenClaw Gateway Watchdog
> 让你的 OpenClaw Gateway 7/24 稳定运行
run-command-safety-check
在执行 shell 方案前检查危险模式，如 pipe-to-shell、覆盖式删除、危险重定向或混淆执行。；use for shell, security, command-review workflows；do not use for 提供攻击性命令, 帮用户绕过限制.
Workplace Safety & OSHA Compliance
Generate workplace safety programs, incident reports, hazard assessments, and compliance documentation.
AI Safety Guard × CMN Team
Prevents AI from accidentally leaking user privacy in all types of outputs. Automatically detects and filters sensitive information (ID cards, bank cards, phone numbers, addresses, medical records, passwords, etc.) across emails, documents, conversations, API responses, screen sharing, and more. This is a behavioral skill - the AI itself becomes privacy-aware, not a filtering tool.