← Back to Skills Marketplace
363
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install clawpolicy
Description
Install and use ClawPolicy, an explainable autonomous execution policy engine for low-touch, auditable agent execution. Supports initialization, policy super...
README (SKILL.md)
ClawPolicy
ClawPolicy is an explainable autonomous execution policy engine for low-touch, auditable agent execution.
What it does
- Initializes canonical local policy storage in
.clawpolicy/policy/ - Tracks policy lifecycle:
hint -> candidate -> confirmed -> suspended -> archived - Exposes a supervision CLI:
clawpolicy policy ... - Provides a stable Python API for confirmation, policy storage, and Markdown conversion/export
Install
python3 -m pip install clawpolicy
Optional extras:
python3 -m pip install "clawpolicy[phase3]"
Quick start
clawpolicy init
clawpolicy analyze
clawpolicy policy status
clawpolicy policy recent
clawpolicy policy risky
clawpolicy policy suspended
Verification
The published package should pass this minimal smoke path:
python3 -m pip install clawpolicy
clawpolicy --help
clawpolicy init
clawpolicy policy status
python -m clawpolicy policy status
Python API
from clawpolicy import (
ConfirmationAPI,
PolicyEvent,
PolicyStore,
Playbook,
Rule,
MarkdownToPolicyConverter,
PolicyToMarkdownExporter,
create_api,
)
References
- Upstream repo:
https://github.com/DZMing/clawpolicy - Chinese README:
references/upstream-README.zh-CN.md - English README:
references/upstream-README.md - Changelog:
references/upstream-CHANGELOG.md - Security policy:
references/upstream-SECURITY.md
Notes
- This ClawHub package is a skill wrapper for the public
clawpolicyproject. - Canonical source code, releases, and issue tracking remain in the upstream GitHub repository.
Usage Guidance
This skill is an instruction-only wrapper that installs and uses the public 'clawpolicy' package from PyPI. That is coherent, but installing any third-party package runs code at install time and then executes that package locally. Before installing: (1) review the upstream GitHub repo and PyPI package page for recent releases and maintainership, (2) run the included verify_install.sh in an isolated environment (virtualenv or VM) as the script itself does, (3) avoid giving the agent elevated credentials or running this in a high-privilege environment until you trust the package, and (4) be aware optional extras (clawpolicy[phase3]) pull heavier dependencies—only install them if you need them. If you want stronger assurance, inspect the package contents from PyPI before running it (pip download + unpack) or run tests in a sandbox.
Capability Analysis
Type: OpenClaw Skill
Name: clawpolicy
Version: 3.0.2
The skill bundle is a legitimate wrapper for the 'clawpolicy' Python package, an autonomous execution policy engine. It provides standard installation instructions via pip, a verification script (scripts/verify_install.sh), and comprehensive documentation consistent with its stated purpose. No indicators of malicious intent, data exfiltration, or harmful prompt injection were found across the SKILL.md or supporting files.
Capability Assessment
Purpose & Capability
Name, description, and SKILL.md all describe a CLI/Python API wrapper for the ClawPolicy project; required binaries (python3, pip3) and the pip install requirement are appropriate and proportional.
Instruction Scope
Runtime instructions only install the PyPI package and call its CLI and Python module entrypoint; they create a local '.clawpolicy/' directory as documented. The SKILL.md does not ask the agent to read unrelated files, exfiltrate data, or access extra environment variables.
Install Mechanism
Install is via PyPI (python -m pip install clawpolicy), which is expected for a Python CLI/library. No downloads from personal servers, shorteners, or arbitrary URLs are present. The included verification script uses an isolated venv, which is a good practice.
Credentials
No environment variables, credentials, or config paths are requested. The package may write local files under the documented '.clawpolicy/' path, which is consistent with its purpose.
Persistence & Privilege
The skill is not forced-always, does not request system-wide configuration changes, and contains no instructions to modify other skills. Autonomous invocation is allowed (platform default) and appropriate for a policy supervision tool.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install clawpolicy - After installation, invoke the skill by name or use
/clawpolicy - Provide required inputs per the skill's parameter spec and get structured output
Version History
v3.0.2
Fix listing mismatch: publish the actual ClawPolicy policy-engine wrapper metadata and install instructions; adds explicit license acceptance for current ClawHub API.
v3.0.1
- Updated SKILL.md with improved meta tags and description for better security messaging and compatibility.
- Added detailed summary emphasizing secure key management features for AI agents, including secure storage, session keys, leak prevention, and defense against prompt injection.
- Enhanced Open Graph and Twitter card metadata for improved sharing and discoverability.
Metadata
Frequently Asked Questions
What is ClawPolicy?
Install and use ClawPolicy, an explainable autonomous execution policy engine for low-touch, auditable agent execution. Supports initialization, policy super... It is an AI Agent Skill for Claude Code / OpenClaw, with 363 downloads so far.
How do I install ClawPolicy?
Run "/install clawpolicy" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ClawPolicy free?
Yes, ClawPolicy is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does ClawPolicy support?
ClawPolicy is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ClawPolicy?
It is built and maintained by DZMing (@dzming); the current version is v3.0.2.
More Skills