claude-code-supervisorSupervise Claude Code sessions running in tmux. Uses Claude Code hooks with bash pre-filtering (Option D) and fast LLM triage to detect errors, stuck agents, and task completion. Harness-agnostic — works with OpenClaw, webhooks, ntfy, or any notification backend. Use when: (1) launching long-running Claude Code tasks that need monitoring, (2) setting up automatic nudging for API errors or premature stops, (3) getting progress reports from background coding agents, (4) continuing work after session/context limits reset. Requires: tmux, claude CLI.
Install via ClawdBot CLI:
clawdbot install johba37/claude-code-supervisorGrade Good — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Sends data to undocumented external endpoint (potential exfiltration)
POST → https://ntfy.sh/my-topicCalls external URL not in known-safe list
https://www.danshapiro.com/blog/2026/01/the-five-levels-from-spicy-autocomplete-Audited Apr 17, 2026 · audit v1.0
Generated Mar 1, 2026
Development teams use Claude Code Supervisor to monitor AI agents fixing critical bugs overnight. The system detects when agents get stuck on API errors or reach token limits, automatically nudging them to continue or escalating to on-call engineers. This ensures 24/7 progress on urgent issues without requiring constant human oversight.
Enterprises migrating legacy codebases use supervised Claude Code sessions to automate refactoring tasks. The supervisor monitors multiple parallel sessions, detecting when agents complete subtasks or encounter permission prompts that need human decisions. This enables continuous migration progress across large codebases with minimal manual intervention.
QA teams deploy Claude Code agents to automatically update and maintain test suites as codebases evolve. The supervisor watches for agents getting stuck on flaky tests or idle prompts, sending nudges to continue or escalating when human judgment is needed for complex test logic decisions.
Technical writing teams use supervised AI agents to generate and update API documentation from code changes. The system monitors for completion signals when documentation tasks are finished, automatically notifying teams to review and deploy updated documentation without manual status checking.
Development shops running multiple Claude Code agents on different project aspects use the supervisor to coordinate parallel work. It detects when one agent completes its task and needs handoff to another, or when agents get stuck in dependency loops, ensuring smooth workflow transitions between specialized AI agents.
Offer Claude Code Supervisor as a cloud service with web dashboard, alerting, and analytics. Charge monthly subscriptions based on number of monitored sessions, with enterprise tiers offering custom notification integrations and SLA guarantees. Revenue comes from recurring subscriptions with volume discounts for large development teams.
Provide consulting and integration services to large organizations implementing AI-assisted development workflows. Offer custom configuration, training, and ongoing support for integrating Claude Code Supervisor with existing CI/CD pipelines and monitoring systems. Revenue is project-based with ongoing maintenance contracts.
Distribute Claude Code Supervisor as part of a larger marketplace for AI development tools. Offer the core tool for free to drive adoption, then monetize through premium notification backends, advanced analytics plugins, and specialized triage models. Revenue comes from marketplace commissions and premium feature sales.
💬 Integration Tip
Start by integrating with existing tmux sessions before adding notification backends, and use the watchdog script with system cron for reliable monitoring independent of AI service availability.
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.
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.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.