daplug

Check AI CLI usage/quota for Claude, Codex, Gemini, Z.AI

Verify daplug configuration status and detect legacy settings

Check if daplug plugin has updates available

Run task with OpenAI Codex CLI (gpt-5.3-codex) (user)

Create an agent-team orchestration bundle (orchestrator prompt + sub-prompts)

Research a library/topic and generate comprehensive llms_txt documentation

You are an expert prompt engineer for Claude Code, specialized in crafting optimal prompts using XML tag structuring and best practices. Your goal is to create highly effective prompts that get things done accurately and efficiently.

Scan and manage available AI coding CLIs

Run task with local Devstral model via Codex CLI + LMStudio (user)

Run task with Google Gemini CLI (user)

Install daplug command bridges for other AI coding runtimes

<objective>

<objective>

Run task with local qwen model via Codex CLI + LMStudio (user)

Run existing prompts with agent-team orchestration (phase groups + auto-deps)

Execute prompts from ./prompts/ with various AI models, optional worktree isolation, tmux sessions, and iterative verification loops

Automated sprint planning from technical specifications

Update documentation and push changes to version control (main repository)

Run task with Z.AI GLM-4.7 via Codex CLI (user)

Validate multi-phase orchestration outputs, detect conflicts, and return PASS/RETRY/ESCALATE decisions.

Resolve complex orchestration failures that require deep reasoning and broad tool access.

Merge and reconcile outputs from parallel orchestration branches, including conflict resolution.

Launch delegated /run-prompt execution, monitor logs/tmux, and emit triage-only execution reports.

Analyze prompt dependencies and produce execution group syntax for /run-at-prompt auto-deps mode.

Frontend build optimization specialist. Proactively analyzes Dockerfiles and CI/CD configs to reduce Node.js/npm build times for SvelteKit, Next.js, Vite, and other frontend frameworks. Use when working on frontend projects, after noticing slow builds, or when optimizing CI/CD pipelines.

Go build optimization specialist. Proactively analyzes Dockerfiles and CI/CD configs to reduce Go compilation times. Use when working on Go projects, after noticing slow builds, or when optimizing CI/CD pipelines.

Infrastructure troubleshooting specialist for VMware/Kubernetes/Storage environments. Use this agent when: <example> Context: User reports disk errors or storage issues user: "The processor-db is getting I/O errors" assistant: "I'll use the infra-troubleshooter agent to diagnose the storage infrastructure." </example> <example> Context: User notices node performance issues user: "storage107 seems slow, can you check it?" assistant: "Let me use the infra-troubleshooter agent to investigate the node health." </example> <example> Context: User asks about VMware or Synology health user: "Are there any issues with our storage nodes?" assistant: "I'll use the infra-troubleshooter agent to perform a comprehensive health check." </example> <example> Context: Log spam or disk space issues user: "The logs are filling up disk space" assistant: "Let me use the infra-troubleshooter agent to identify and fix the log issues." </example> Trigger conditions: - Disk I/O errors or Medium Error SCSI conditions - Node performance degradation - Log spam or excessive disk usage - Orphaned pods or stale kubelet state - Longhorn volume health issues - VMware virtual disk problems - Synology NAS backend issues - Storage node health checks

Use this agent when: <example> Context: User reports that the backend service is not responding in staging. user: "The backend isn't working in staging, can you check what's wrong?" assistant: "I'll use the k8s-cicd-troubleshooter agent to diagnose the backend service issue in the staging environment." <commentary> The user is reporting a service outage in a deployed environment. Use the Task tool to launch the k8s-cicd-troubleshooter agent to investigate pod status, logs, and deployment health. </commentary> </example> <example> Context: User notices CI/CD pipeline failing during the test stage. user: "The pipeline keeps failing on test-integration, what's happening?" assistant: "Let me use the k8s-cicd-troubleshooter agent to analyze the pipeline failure and trace the test-integration job logs." <commentary> The user is experiencing a CI/CD pipeline failure. Use the k8s-cicd-troubleshooter agent to investigate using glab CLI tools and analyze job artifacts. </commentary> </example> <example> Context: User completes a code change and deployment. user: "I just deployed the new feature to production" assistant: "Let me use the k8s-cicd-troubleshooter agent to verify the deployment rolled out successfully and check pod health." <commentary> After a deployment, proactively use the k8s-cicd-troubleshooter agent to verify the rollout status and ensure no issues occurred. </commentary> </example> <example> Context: User mentions persistent storage issues. user: "The scheduler config keeps resetting every time the pod restarts" assistant: "I'll use the k8s-cicd-troubleshooter agent to investigate the persistent volume configuration and verify the mount paths." <commentary> This is a persistent storage issue common in Kubernetes. Use the k8s-cicd-troubleshooter agent to diagnose PVC mounts and storage patterns. </commentary> </example> <example> Context: User asks about resource usage. user: "Are we hitting memory limits on any pods?" assistant: "Let me use the k8s-cicd-troubleshooter agent to check resource usage across all deployments." <commentary> Resource monitoring is a core Kubernetes troubleshooting task. Use the k8s-cicd-troubleshooter agent to analyze pod metrics. </commentary> </example> Trigger conditions: - Service outages or degraded performance in staging/production - Pod crashes, restarts, OOMKills, or CrashLoopBackOff states - Deployment failures or stuck rollouts - CI/CD pipeline failures (build, test, deploy stages) - Persistent volume or configuration issues - Database connectivity problems - Job queue processing failures - Configuration drift between environments - Post-deployment verification checks - Resource usage analysis or capacity planning - GitOps Fleet sync issues or deployment mismatches

Monitors CI/CD pipeline after git push and orchestrates deployment verification workflow. Use this agent when: <example> Context: User just pushed changes to origin user: "Just pushed, can you watch the pipeline?" assistant: "I'll use the pipeline-deploy-monitor agent to monitor the CI/CD pipeline and verify deployments." </example> <example> Context: User wants full deployment verification user: "Push this to staging and production with full verification" assistant: "Let me use the pipeline-deploy-monitor agent to handle the deployment workflow." </example> <example> Context: After committing changes user: "Deploy this change" assistant: "I'll use the pipeline-deploy-monitor agent to push, monitor the pipeline, and verify staging before production." </example> Trigger conditions: - After git push to origin - User requests deployment verification - User asks to monitor pipeline status - User wants staging verification before production - Post-commit deployment workflows

Monitors log files and state files for prompt execution. READ-ONLY - no file modifications, no bash commands. Use for background monitoring of CLI executions.

Check AI CLI usage/quota for Claude Code, OpenAI Codex, Google Gemini CLI, and Z.AI. Use when user asks about remaining quota, usage limits, rate limits, or wants to check how much capacity is left.

Create agent-team orchestrated prompt bundles (orchestrator + sub-prompts) and store them through prompt-manager.

Orchestrate multi-prompt execution with phase groups, optional auto-deps, and model-tiered agent roles.

Detect installed AI coding CLIs and local model providers; outputs a cached JSON inventory for routing (/detect-clis).

Read and manage daplug configuration from CLAUDE.md using <daplug_config> blocks, with legacy fallback and migration support.

Execute prompts from ./prompts/ directory with various AI models. Use when user asks to run a prompt, execute a task, delegate work to an AI model, run prompts in worktrees/tmux, or run prompts with verification loops.

Find and resolve prompt files in ./prompts/ directory. Use when user asks to find a prompt, list available prompts, locate prompt by number or name, or check what prompts exist.

CRUD operations for prompt files. Centralizes all prompt management logic to avoid shell parsing issues and provide consistent behavior across commands.

Automated sprint planning and execution from technical specifications (prompt generation, dependency planning, stateful execution)

Manage tmux sessions for background tasks. Use when user asks about background processes, wants to monitor running tasks, attach to sessions, list active sessions, or kill stuck processes.

Manage git worktrees for isolated development. Use when user asks to create isolated workspaces, work on multiple branches simultaneously, set up parallel development environments, or clean up old worktrees.

1 hook across 1 event