By panicgit
Design and run multi-agent harnesses (Planner → Generator → Evaluator) for complex, long-running AI tasks
Interactive harness design wizard. Analyzes a project's single-agent failures, diagnoses root causes, and generates a custom multi-agent harness config (.wrangler/harness.json) with tailored system prompts. Trigger: "design harness", "harness design", "하네스 설계", "에이전트 설계", "multi-agent design", "멀티 에이전트 설계"
List all agents in the current harness. Shows agent names, roles, models, workflow sequence, handoff files, and current sprint status. Usage: /wrangler:list Trigger: "list agents", "show agents", "에이전트 목록", "하네스 목록"
Invoke an agent from a designed harness. Reads .wrangler/harness.json to find the agent config, loads its system prompt, and spawns it via the Agent tool. Manages sprint directories and inter-agent communication files automatically. Usage: /wrangler:run <agent-name> Trigger: "run agent", "run harness", "에이전트 실행", "하네스 실행"
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Automated Android app testing with 3-tier strategy (text → uiautomator → screenshot) powered by Claude Code
npx claudepluginhub panicgit/wrangler --plugin wranglerA single-skill package for generating harness blueprints for agentic systems.
This skill should be used when the model's ROLE_TYPE is orchestrator and needs to delegate tasks to specialist sub-agents. Provides scientific delegation framework ensuring world-building context (WHERE, WHAT, WHY) while preserving agent autonomy in implementation decisions (HOW). Use when planning task delegation, structuring sub-agent prompts, or coordinating multi-agent workflows.
Long Task Harness for AI agents - task/feature-driven development with external memory
Task distribution, agent coordination, progress monitoring - executes plans via subagents. Requires AI Maestro for inter-agent messaging.
HelloAGENTS — The orchestration kernel that makes any AI CLI smarter. Adds intelligent routing, unified QA gates, safety guards, and notifications.
Repowire mesh usage skills for AI coding agents: cross-agent review and planning, delegate, usage patterns, and install/update. Backend-agnostic and parameterised on the agent you choose.