Agentic Workflow

This is a structured pipeline for breaking down implementation tasks across specialized agents. Each stage (research, planning, validation, implementation, review) runs as a background task that writes outputs to the filesystem instead of flooding your main context. The pattern enforces TDD and uses NIA Oracle for research upfront, then hands off artifacts between agents via markdown files in .claude/cache/agents/. The key insight here is using file-based handoff instead of TaskOutput to avoid 70k token transcripts clogging your conversation. It's orchestration code, meant to keep your main context clean while agents do the heavy lifting in isolation.

skills.sh installs: 567
GitHub stars: 3.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add parcadei/continuous-claude-v3 --skill agentic-workflow --agent claude-code

Installs into .claude/skills of the current project.

Files

Agentic Workflow Pattern

Standard multi-agent pipeline for implementation tasks.

Architecture Principles

Use run_in_background: true for all agents to keep main context minimal
Use Task tool (never TaskOutput) to avoid receiving full agent transcripts
Agents write outputs to .claude/cache/agents/<stage>/ for injection into subsequent agents
Main conversation is pure orchestration — no heavy lifting, only coordination

Workflow Stages

1. Research Agent

Task(subagent_type="oracle", run_in_background=true, prompt="""
Query NIA Oracle (via /nia-docs skill) to verify approach and gather best practices.

Output to: .claude/cache/agents/oracle/<task>-research.md
""")

Enforce NIA as the research layer
Output: Research findings

2. Planning Agent

Task(subagent_type="plan-agent", run_in_background=true, prompt="""
Read: .claude/cache/agents/oracle/<task>-research.md
Use RP-CLI to analyze the target codebase section.
Generate implementation plan informed by research.

Output to: .claude/cache/agents/plan-agent/<task>-plan.md
""")

Receives: Research agent output as context
Output: Implementation plan

SKILL.md on GitHub