Skip to main content
skill CX Codex

agentic-workflow — Claude Code skill: what it does, how to install

The agentic-workflow skill organizes implementation work into research, planning, validation, coding, and review. Separate agents handle each stage in the background.

MIT ★ 3,951 updated 2026-01-26

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a claude-code
Open on GitHub

What agentic-workflow does

The workflow assigns five stages to agents. One gathers guidance through NIA Oracle and /nia-docs; another examines the target codebase with RP-CLI and drafts a plan. Further agents validate that plan, implement it, then review the changes and run tests.

Agents work in the background and pass results through files under .claude/cache/agents/, leaving the main session to coordinate. The described process relies on NIA Oracle, /nia-docs, and RP-CLI. A missing expected file or a stalled output file can signal a stuck task, so the skill recommends monitoring progress reminders and filesystem output.

What it helps with

  • split implementation work into defined stages
  • pass research findings to a planning agent
  • check a plan against research before coding
  • write failing tests before implementation
  • compare completed work with the plan and research

Example prompts for the agent

  • Run this implementation task through the skill's research, planning, validation, coding, and review stages.
  • Research the recommended approach with NIA Oracle and /nia-docs, then analyze the target code with RP-CLI.
  • Implement the validated plan by writing failing tests first, then run the tests again after coding.

How to install agentic-workflow

1Skills CLI (Vercel)

npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a claude-code

2Manually: put the files in place

~/.claude/skills/agentic-workflow/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/agentic-workflow/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about agentic-workflow

How do I install agentic-workflow in Claude Code?

Run npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a claude-code. The skill file is at ~/.claude/skills/agentic-workflow/SKILL.md.

What does agentic-workflow do?

It routes implementation through five background stages: research, planning, plan validation, implementation, and review. Agents pass their work to later stages through files.

How do agents hand off their work?

Each stage writes its result under .claude/cache/agents/, where the next agent can read it. The main session coordinates the workflow instead of pulling full agent transcripts.

Source text

SKILL.md · MIT
---
name: agentic-workflow
description: Agentic Workflow Pattern
user-invocable: false
---

# 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

### 3. Validation Agent
```
Task(subagent_type="validate-agent", run_in_background=true, prompt="""
Read: .claude/cache/agents/plan-agent/<task>-plan.md
Read: .claude/cache/agents/oracle/<task>-research.md
Review 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.md
Read: .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.md
Read: .claude/cache/agents/validate-agent/<task>-validated.md
Read: .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
```

**Stuck detection:**
1. Progress reminders stop arriving
2. Task output file size stops growing
3. 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
```

## Key Rules

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

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

© parcadei · MIT · parcadei/Continuous-Claude-v3

Similar skills

All skills for Agent setup: memory, context, orchestration →

From the same set161

The whole set →
rings A Claude Code skill with decision trees and tools for abstract algebra problems on rings. Verifies ring axioms, analyzes properties, and manipulates ideals using Z3 and SymPy. CX Codex +1 ★ 3,951repo stars critic critic reviews features and implementations for logic issues, test gaps, and mismatches with repository patterns, then saves its findings to a Markdown file. CX Codex ★ 3,951repo stars numerical-integration A skill for numerical integration in mathematical analysis tasks. Guides you through selecting a quadrature method, setting tolerances, and computing integrals via scipy and sympy. CX Codex +1 ★ 3,951repo stars groups Structures problem-solving in group theory. Activates when the agent needs to verify group axioms, test subgroups, or prove homomorphisms. CX Codex +1 ★ 3,951repo stars graph-algorithms graph-algorithms — a Claude Code skill with a decision tree for graph algorithm problems: traversals, shortest paths, spanning trees, network flow, and spectral analysis. Runs Z3 and SymPy via uv run from inside the agent. CX Codex +1 ★ 3,951repo stars residues A Claude Code skill for solving residue problems in complex analysis. Computes residues at poles, identifies pole order, and applies the residue theorem through SymPy and Z3. CX Codex +1 ★ 3,951repo stars hilbert-spaces Solves functional analysis problems involving Hilbert spaces. Use it for orthogonal decomposition, projection theorems, Riesz representation, and computations on orthonormal bases. CX Codex +1 ★ 3,951repo stars debug-agent debug-agent — a subagent that investigates root causes by exploring the codebase, analyzing logs, finding patterns, and writing a detailed report with fix recommendations. CX Codex ★ 3,951repo stars

Project sponsors

Companies that keep this analytics open