Argus is a persistent testing agent that monitors commits, enriches metadata, and runs incremental backend and frontend tests.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install argus-qa
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 argus-qa 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 Argus?
Argus is a comprehensive quality assurance agent designed to integrate seamlessly into your development environment as part of the Openclaw Skills ecosystem. It acts as a hundred-eyed monitor that never sleeps, ensuring every fixed bug remains fixed through a persistent test catalog. It bridges the gap between manual coding and automated verification by scanning routes, mining git history for regressions, and maintaining a source of truth for project health.
By leveraging persistent memory, Argus tracks the lifecycle of every test from generation to active status. It intelligently differentiates between regenerable tests and locked tests that protect vital business logic. This skill is essential for developers using Openclaw Skills who want to maintain high code quality without the overhead of manually managing complex test suites, providing a robust safety net for every commit.
Argus Use Cases
- Automating API testing for backend routes discovered during source code analysis.
- Ensuring bug fixes are permanently verified via locked test entries managed by Openclaw Skills.
- Improving git history clarity by automatically enriching insufficient commit messages with technical diff context.
- Reducing test execution time by running scoped tests based on specific branch changes.
- Monitoring frontend regressions through automated Playwright browser flows and failure screenshots.
How Argus Works
- Initialize the system via /argus init to bootstrap the test catalog and scan for existing endpoints and bug history.
- The skill installs a post-commit hook to monitor changes and enrich commit messages within the Openclaw Skills environment.
- Upon new commits, Argus updates its catalog, identifying whether new tests are needed based on modified files or inferred bug fixes.
- Backend and frontend test code is automatically generated and appended to the test suite using pytest and Playwright.
- Tests are executed either on-demand or incrementally, checking the health of the local server and browser flows.
- A detailed Markdown report is generated, providing a health score and identifying coverage gaps for the AI agent to address.
Argus Setup
To get started with Argus in Openclaw Skills, run the initialization command within your project root:
/argus init
Ensure your environment variables are configured for testing to allow the agent to reach your local servers:
export TEST_BASE_URL="http://localhost:8000"
export TEST_APP_URL="http://localhost:3000"
The setup will automatically mine your git history and install the necessary hooks in .git/hooks/post-commit to enable continuous monitoring.
Argus Data Schema & Taxonomy
Argus organizes its internal data and knowledge within a dedicated .argus/ directory to maintain persistence within Openclaw Skills:
| Path | Purpose |
|---|---|
| .argus/catalog.md | Markdown-based database of all tests, statuses, and protection levels. |
| .argus/baseline.json | JSON storage for health score history and performance metrics. |
| .argus/reports/ | Directory for date-stamped test reports and failure screenshots. |
| .argus/commit-hook.sh | Logic for the git post-commit monitoring and enrichment phase. |
Argus Advanced Features
- Intelligent commit message enrichment that scores and amends messages for better project traceability.
- Support for incremental test runs using the --diff flag to focus only on changed code paths.
- Automated browser testing infrastructure that manages Playwright dependencies and captures visual evidence on failure.
- High-risk endpoint identification to prioritize testing for auth, payments, and data-writing operations.
- Permanent protection for critical regression tests using the locked status within the Openclaw Skills framework.
SKILL.md
Loading
Related Openclaw Skills
House Price Tracker
An AI-driven real estate tool for retrieving city-specific house prices, growth trends, and visual market reports.
Send To Me - WeChat Enterprise Messaging
A professional messaging utility for sending structured reports, alerts, and notifications directly to WeChat Enterprise (WeCom).
Disk Guardian
A comprehensive drive health monitoring and diagnostic suite that uses S.M.A.R.T. data to predict and report hardware failures.
Homelab Runbook
An automated scanning tool that generates comprehensive Markdown runbooks documenting Docker containers, system services, and open network ports.
Test Collection Skill
A diagnostic utility designed to validate the discovery, priority coverage, and configuration injection mechanisms of AI agent environments.
News Digest Aggregator
A daily automated system that aggregates RSS feeds, summarizes content via AI, and delivers formatted digests to messaging platforms.
Featured*
