A utility for inspecting local OpenClaw database policies including auto-approval settings and skill availability.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install read-policy
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install read-policy using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Read Policy?
The Read Policy skill is a specialized administrative utility designed to interface directly with the OpenClaw database layer. It enables developers and AI agents to query the public.openclaw_policies table within a local Supabase Docker environment. This capability is essential for verifying active configurations and ensuring that agent behavior aligns with defined system rules.
By leveraging this tool, users can gain immediate visibility into critical operational parameters such as priority routing and auto-approval flags. As part of the broader ecosystem of Openclaw Skills, it provides a bridge between high-level agent logic and the underlying data persistence layer, facilitating safer and more transparent automation.
Read Policy Use Cases
- Verifying if auto_approve is enabled before triggering high-stakes autonomous workflows.
- Auditing priority_routing settings to troubleshoot task execution order.
- Listing all available_skills currently registered in the local environment.
- Inspecting system-wide policy keys during development and debugging sessions.
How Read Policy Works
- The skill invokes a localized shell script that targets the supabase-db Docker container.
- It executes a SQL query against the public.openclaw_policies table using docker exec.
- The script parses the database output to return either a specific key-value pair or a full list of policies.
- The result is returned to the agent or terminal for inspection and further logic processing.
Read Policy Setup
Ensure your local Supabase environment is running, then use the provided script within your Openclaw Skills directory:
# Grant execution permissions to the script
chmod +x scripts/read-policy.sh
# Test the connection by listing policies
./scripts/read-policy.sh list
Read Policy Data Schema & Taxonomy
The skill interacts with the public.openclaw_policies table. Data is typically returned as a string or a list of key-value pairs.
| Key | Type | Description |
|---|---|---|
auto_approve |
boolean | Determines if actions require manual human intervention. |
priority_routing |
string/enum | Defines the logic for task distribution. |
available_skills |
array | Lists the active capabilities registered in the system. |
Read Policy Advanced Features
- Direct Docker Integration: Bypasses complex API layers by interacting directly with the supabase-db container.
- Precision Querying: Supports fetching individual configuration keys to minimize data overhead for AI agents.
- Zero-Config Inspection: Designed for read-only access to prevent accidental modification of production-level policies while using Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
polaris-news
Verified news intelligence providing real-time, bias-scored briefs across 18 specialized verticals for AI agents.
Daum Toy Search
A high-performance search skill for Korean web results featuring Kakao index integration and intelligent reranking for AI agents.
Screen Recommendation Loop
An automated recommendation engine that builds long-term movie and anime taste profiles through iterative feedback loops.
Daily Commits Summary
A specialized tool that analyzes git history to generate human-readable daily summaries grouped by feature and functional area.
Addition Assistant
A precise arithmetic utility designed to parse and calculate addition expressions from diverse input formats.
YOAP Communication Protocol
A comprehensive A2A protocol designed to connect people through intelligent agent matching and secure communication.
Featured*
