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
npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a claude-codeWhat 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-code2Manually: put the files in place
~/.claude/skills/agentic-workflow/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/agentic-workflow/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a codex2Manually: put the files in place
.agents/skills/agentic-workflow/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a cursor2Manually: put the files in place
.cursor/skills/agentic-workflow/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 .claude/skills/agentic-workflow2Manually: put the files in place
.github/skills/agentic-workflow/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill agentic-workflow -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/skills/agentic-workflowManually: put the files in place
.devin/skills/agentic-workflow/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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