skills.rest
asfbay-bit
asfbay-bitCOMMUNITY
Explore all skills by this author →
GitHub

oc-agent-forge

Develop Claude Agent SDK applications with planning, building, and evaluation loops.

Updated May 15, 2026
Search Tags:#agent development#multi-agent system#agent evaluation#claude agent#harness loop#tool budget
One-click install
npx skills add https://github.com/asfbay-bit/opchain-skills --skill oc-agent-forge
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: oc-agent-forge
Source: https://github.com/asfbay-bit/opchain-skills/tree/main/skills/oc-agent-forge
Command: npx skills add https://github.com/asfbay-bit/opchain-skills --skill oc-agent-forge

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires oc-claude-api, oc-rag-forge, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the development of Claude Agent SDK applications by providing a comprehensive framework that includes a Planner/Builder/Evaluator loop, subagent topology management, tool budgets, harness loop shapes, and agent evaluation. It addresses the challenges of designing, building, and evaluating multi-agent systems, enabling efficient development of robust and efficient Claude Agent SDK apps.

Core Features & Use Cases

  • Planner/Builder/Evaluator Loop: Facilitates the systematic development of Claude Agent SDK apps, from planning the agent topology and tool budget to building the harness and evaluating the agent.
  • Subagent Topology Management: Offers the flexibility to design and manage subagent topologies for single-agent, orchestrator-worker, pipeline, and hierarchical architectures.
  • Tool Budgets: Allows the definition of tool allowlists, call ceilings, and deferred-loading for efficient tool usage and cost management.
  • Harness Loops: Provides options for react, plan-execute, and reflect/critique loop shapes to accommodate various task structures and requirements.
  • Agent Evaluation: Evaluates the agent's performance against a fixture suite, considering task success, trajectory, tool efficiency, and cost.
  • Use Case: Suppose you need to develop a Claude Agent SDK app for a multi-step task that involves research, data processing, and decision-making. Use this Skill to design the agent's topology, define the tool budget, build the harness, and evaluate the agent's performance.

Quick Start

Use the /oc-agent command to design, build, and evaluate a Claude Agent SDK app.

Frequently Asked Questions about oc-agent-forge

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I build a multi-agent system with the Claude Agent SDK?▼

Build a multi-agent system by defining subagent topologies like orchestrator-worker or pipeline, setting tool budgets, and implementing harness loops. The framework manages planning, building, and evaluating agents for complex tasks.

What is a Planner/Builder/Evaluator loop for agent development?▼

A Planner/Builder/Evaluator loop systematically develops agents by planning the topology and tool budget, building the harness, and evaluating the agent's performance against a fixture suite for task success and tool efficiency.

How do I manage tool budgets and call ceilings in a Claude agent?▼

Manage tool budgets by defining tool allowlists, setting call ceilings, and using deferred-loading. This ensures efficient tool usage and controls costs when developing Claude Agent SDK applications.

Can I use different harness loop shapes like react or plan-execute for my agent?▼

Yes, you can use react, plan-execute, and reflect/critique harness loop shapes. These options accommodate various task structures and requirements when building Claude Agent SDK applications.

How do I evaluate multi-agent system performance and trajectory?▼

Evaluate multi-agent system performance by running the agent against a fixture suite. The evaluation considers task success, trajectory, tool efficiency, and cost to measure the agent's effectiveness.

Do I need oc-claude-api and oc-rag-forge to develop an agent topology?▼

You need oc-claude-api for model routing and oc-rag-forge for retrieval when developing agent topologies. These dependencies provide the foundational model access and retrieval capabilities required by the framework.

Related Skills

Explore More Software Engineering Skills→
asfbay-bitasfbay-bit

oc-prompt-ops

Manage prompt versioning, evaluation, and drift detection for LLMs.

Community
Advanced
reaatechreaatech

Cost Tracking

Calculates per-task and per-trajectory costs for AI evaluation workflows.

Community
Advanced
Adam-GuerinAdam-Guerin
1

rag-implementation

Guide RAG system implementation covering embeddings, vector databases, chunking, retrieval, and LLM integration.

Community
Advanced
ijindal1ijindal1

openai-advanced-agents

Design and implement tool-using agents with OpenAI models.

Community
Advanced