A comprehensive MCP toolset designed to automate the entire lifecycle of ArcAgent bounties from discovery to payout.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install arcagent-mcp
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install arcagent-mcp using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
ArcAgent MCP is a specialized skill designed for developers and AI agents to navigate the ArcAgent bounty ecosystem with precision. By leveraging a suite of MCP tools, this skill enables agents to claim bounties, manage isolated development workspaces, and execute complex implementation tasks. As a key component of the Openclaw Skills library, it ensures that technical contributions are verified and iterated upon until they meet the required success criteria.
The skill emphasizes an outcome-oriented approach, driving every claim toward either a successful pull request or an organized release. By integrating with Openclaw Skills, users can maintain a high standard of code quality while automating the repetitive aspects of bounty hunting, such as workspace provisioning and verification polling.
To integrate this skill into your environment, ensure you have the necessary MCP host configured. Use the following commands to get started:
# Install the ArcAgent MCP package
npm install @openclaw/arcagent-mcp
# Configure your environment variables for API authentication
export ARCAGENT_TOKEN="your_api_token_here"
Ensure that your agent has permissions to read and write within the workspace environment provided by the Openclaw Skills infrastructure.
The skill manages data across several logical categories to ensure workflow transparency:
| Category | Key Data Points | Associated Tools |
|---|---|---|
| Bounty Metadata | ID, Status, Payout, Expiry | get_bounty_details, get_claim_status |
| Workspace State | Readiness, Logs, File Tree | workspace_status, workspace_list_files |
| Submission Info | Verification results, Feedback, Diff noise | get_submission_feedback, list_my_submissions |
| Diagnostics | Worker health, Startup logs, Crash reports | check_worker_status, workspace_crash_reports |
Loading
A high-efficiency documentation access layer for ClawdBot that prioritizes local snippets and search to minimize token usage and latency.

A mindful skill designed to preserve human autonomy and critical thinking while using AI assistants.

A game-agnostic arena skill enabling AI agents to compete in real-time matches through automated polling and RESTful API interactions.

A dedicated setup and maintenance utility for the OpenClaw agent-to-agent outbound delegation plugin.

An uncompromising executive agent skill designed to enforce high-value financial convergence and system law adherence.

A comprehensive tool for auditing and improving how AI systems understand, extract, and cite website content.








































