Agentic Workflow

by parcadeid07ff4b06b62No license3.9K starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 8 months ago

Agentic Workflow Pattern

Instructions onlyAI & Agents Software Development

AI-generated overview

Defines a five-stage multi-agent pipeline for implementation tasks, with file-based handoff between research, planning, validation, implementation and review…

What it does: This skill documents a standard multi-agent workflow pattern for implementation work. It specifies five stages — research, planning, validation, implementation and review — each run as a background subagent that writes its output to a file under .claude/cache/agents/ /, which the next stage reads as context. It also covers progress monitoring, stuck detection and a directory layout for the handoff artifacts.
When to use it: Use it when orchestrating a multi-agent pipeline for a coding implementation task and you want a defined stage order with file-based handoffs. It suits setups where the main conversation should stay as pure orchestration and agents run in the background.
Requirements: Instructions only; no scripts ship with the skill. It assumes an agent environment with a Task tool and background subagents, plus the named subagent types (oracle, plan-agent, validate-agent, agentica-agent, review-agent), the /nia-docs skill, NIA Oracle, RP-CLI, and a writable .claude/cache/agents/ directory.

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""")

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.mdUse RP-CLI to analyze the target codebase section.Generate implementation plan informed by research.
Output to: .claude/cache/agents/plan-agent/<task>-plan.md""")

Task(subagent_type="plan-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/oracle/<task>-research.mdUse 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

3. Validation Agent

Task(subagent_type="validate-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/plan-agent/<task>-plan.mdRead: .claude/cache/agents/oracle/<task>-research.mdReview plan against research findings and best practices.
Output to: .claude/cache/agents/validate-agent/<task>-validated.md""")

Task(subagent_type="validate-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/plan-agent/<task>-plan.mdRead: .claude/cache/agents/oracle/<task>-research.mdReview plan against research findings and best practices.
Output to: .claude/cache/agents/validate-agent/<task>-validated.md""")

Reviews plan against research
Output: Validated plan with amendments

4. Implementation Agent

Task(subagent_type="agentica-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/validate-agent/<task>-validated.mdRead: .claude/cache/agents/oracle/<task>-research.md
TDD approach: Write failing tests FIRST, then implement.Run tests to verify.
Output summary to: .claude/cache/agents/implement-agent/<task>-implementation.md""")

Task(subagent_type="agentica-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/validate-agent/<task>-validated.mdRead: .claude/cache/agents/oracle/<task>-research.md
TDD approach: Write failing tests FIRST, then implement.Run tests to verify.
Output summary to: .claude/cache/agents/implement-agent/<task>-implementation.md""")

Receives: Validated plan + research context
TDD: Failing tests first
Output: Implementation + tests

5. Review Agent

Task(subagent_type="review-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/implement-agent/<task>-implementation.mdRead: .claude/cache/agents/validate-agent/<task>-validated.mdRead: .claude/cache/agents/oracle/<task>-research.md
Cross-reference implementation against plan and research.Run tests to confirm passing.
Output to: .claude/cache/agents/review-agent/<task>-review.md""")

Task(subagent_type="review-agent", run_in_background=true, prompt="""Read: .claude/cache/agents/implement-agent/<task>-implementation.mdRead: .claude/cache/agents/validate-agent/<task>-validated.mdRead: .claude/cache/agents/oracle/<task>-research.md
Cross-reference implementation against plan and research.Run tests to confirm passing.
Output to: .claude/cache/agents/review-agent/<task>-review.md""")

Cross-references all artifacts
Confirms tests pass
Output: Review summary

Agent Progress Monitoring

bash

# Watch for system reminders:# "Agent a42a16e progress: 6 new tools used, 88914 new tokens"
# Poll for output files:find .claude/cache/agents -name "*.md" -mmin -5
# Check task file size growth:wc -c /tmp/claude/.../tasks/<id>.output

# Watch for system reminders:# "Agent a42a16e progress: 6 new tools used, 88914 new tokens"
# Poll for output files:find .claude/cache/agents -name "*.md" -mmin -5
# Check task file size growth:wc -c /tmp/claude/.../tasks/<id>.output

Stuck detection:

Progress reminders stop arriving
Task output file size stops growing
Expected output file not created after reasonable time

Directory Structure

.claude/cache/agents/├── oracle/│   └── <task>-research.md├── plan-agent/│   └── <task>-plan.md├── validate-agent/│   └── <task>-validated.md├── implement-agent/│   └── <task>-implementation.md└── review-agent/    └── <task>-review.md

.claude/cache/agents/├── oracle/│   └── <task>-research.md├── plan-agent/│   └── <task>-plan.md├── validate-agent/│   └── <task>-validated.md├── implement-agent/│   └── <task>-implementation.md└── review-agent/    └── <task>-review.md

Key Rules

Never use TaskOutput - floods context with 70k+ token transcripts
Always run_in_background=true - isolates agent context
File-based handoff - each agent reads previous agent's output file
Poll, don't block - check file system for outputs, don't wait
TDD in implementation - failing tests first, then make them pass

Source

Session 2026-01-01: SDK Phase 3 implementation using this pattern

Source and attribution

Source:parcadei/continuous-claude-v3in.claude/skills/agentic-workflowat commitd07ff4b

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Agentic Workflow

Agentic Workflow Pattern

Architecture Principles

Workflow Stages

1. Research Agent

2. Planning Agent

3. Validation Agent

4. Implementation Agent

5. Review Agent

Agent Progress Monitoring

Directory Structure

Key Rules

Source

Source and attribution

More from parcadei/continuous-claude-v3

Tldr Stats

Wiring

Workflow Router

Validate Agent

Tour

Tldr Overview

More in AI & Agents

Ppt Template Creator

Skill Development

Plugin Structure

Command Development

Claude Md Improver

Find Skills