This is the infrastructure for chaining Claude prompts together where each step feeds into the next. You get two modes: custom chains where you pass your own prompts in sequence, or predefined pipelines for analysis, refactoring, testing, and optimization. The real value is in avoiding the copy-paste loop when you're doing multi-step transformations. Security audits that flow from vulnerability scan to categorization to fixes, or data pipelines that extract, normalize, validate, and report. Each step gets the full output from the previous one as context. The pipelines are opinionated but customizable through config files if you find yourself running the same chains repeatedly. It's streaming JSON under the hood, which matters for longer workflows.

GitHub stars
240
last updated
Jun 11, 2026

Install

$ npx -y skills add spencermarx/open-code-review --skill stream-chain --agent claude-code

Installs into .claude/skills of the current project.

Files

Stream-Chain Skill

Execute sophisticated multi-step workflows where each agent's output flows into the next, enabling complex data transformations and sequential processing pipelines.

Overview

Stream-Chain provides two powerful modes for orchestrating multi-agent workflows:

  1. Custom Chains (run): Execute custom prompt sequences with full control
  2. Predefined Pipelines (pipeline): Use battle-tested workflows for common tasks

Each step in a chain receives the complete output from the previous step, enabling sophisticated multi-agent coordination through streaming data flow.


Quick Start

Run a Custom Chain

claude-flow stream-chain run \
  "Analyze codebase structure" \
  "Identify improvement areas" \
  "Generate action plan"

Execute a Pipeline

claude-flow stream-chain pipeline analysis

Custom Chains (run)

Execute custom stream chains with your own prompts for maximum flexibility.

Syntax

claude-flow stream-chain run <prompt1> <prompt2> [...] [options]

Requirements:

  • Minimum 2 prompts required
  • Each prompt becomes a step in the chain
  • Output flows sequentially through all steps

Sponsors

Details

Repository
github.com/spencermarx/open-code-review
Categories
Git & Pull Requests, Code Review & Quality, AI & Agent Building
License
Apache-2.0
First seen
Jun 11, 2026

More from spencermarx/open-code-review

All 31
1spencermarx avatarswarm-advancedspencermarx/open-code-reviewAdvanced swarm orchestration patterns for research, development, testing, and complex distributed workflows0skills.sh installs
2spencermarx avatarSwarm Orchestrationspencermarx/open-code-reviewOrchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single age0skills.sh installs
3spencermarx avatarV3 CLI Modernizationspencermarx/open-code-reviewCLI modernization and hooks system enhancement for claude-flow v3. Implements interactive prompts, command decomposition, enhanced hooks integration, and intell0skills.sh installs
4spencermarx avatarV3 Core Implementationspencermarx/open-code-reviewCore module implementation for claude-flow v3. Implements DDD domains, clean architecture patterns, dependency injection, and modular TypeScript codebase with c0skills.sh installs
5spencermarx avatarV3 DDD Architecturespencermarx/open-code-reviewDomain-Driven Design architecture for claude-flow v3. Implements modular, bounded context architecture with clean separation of concerns and microkernel pattern0skills.sh installs
6spencermarx avatarV3 Deep Integrationspencermarx/open-code-reviewDeep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parall0skills.sh installs