agent-pipelineManages code task workflow by spawning sub-agents for research, coding, reviewing, security audit, testing, and committing with detailed logging and updates.
Install via ClawdBot CLI:
clawdbot install curbob/agent-pipelineGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → http://10.0.0.40:3000/api/board/projects/{project}/items`Calls external URL not in known-safe list
http://10.0.0.40:3000/api/board/projects/{project}/items`AI Analysis
The external API call is consistent with the skill's stated purpose of logging to a board for project management. The endpoint appears to be an internal development server (10.0.0.40), not a public unauthorized service, and there is no evidence of credential harvesting, user data exfiltration, or hidden malicious instructions.
Audited Apr 17, 2026 · audit v1.0
Generated Mar 20, 2026
A team needs to add a new API endpoint with authentication to an existing web app. The pipeline ensures code is written, reviewed for security vulnerabilities like injection, tested for compilation, and properly committed with documentation.
Refactoring outdated code in a financial system to improve performance and maintainability. The pipeline uses the Researcher to understand existing patterns, then applies changes with security audits to prevent data exposure issues.
Implementing security patches for an e-commerce site to address CSRF and XSS risks. The pipeline coordinates coding, review, and testing stages to ensure updates are minimal in scope and do not break existing functionality.
Integrating a third-party payment API into a mobile app. The pipeline leverages the Researcher for API documentation, followed by coding, security checks for auth issues, and testing to verify build and structural correctness.
Offers custom development services using the pipeline to streamline client projects. Ensures consistent quality, security, and documentation, reducing rework and improving client satisfaction through structured workflows.
Provides the pipeline as a SaaS tool for development teams. Integrates with existing CI/CD systems, charging per user or project to help teams automate code reviews, security audits, and testing processes.
Consultants implement the pipeline for large organizations to improve internal development practices. Focuses on training, integration with legacy systems, and ongoing support to enhance code quality and security compliance.
💬 Integration Tip
Ensure all agents have access to auth-profiles.json and integrate the Board API for logging to track pipeline progress and issues in real-time.
Scored Apr 19, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Coding style memory that adapts to your preferences, conventions, and patterns for consistent coding.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.