Skip to main content
ClaudeWave
ES, Spanish
parcadei / Subagents

Continuous-Claude-v3

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

  • 3.9k estrellas
  • 302 forks
  • 47 issues abiertos
  • Lenguaje: Python
  • Licencia: MIT
  • actualizado
Instalar en ClaudeVer en GitHub

Instalación

Terminal
git clone https://github.com/parcadei/Continuous-Claude-v3 && cp Continuous-Claude-v3/*.md ~/.claude/agents/
  1. Clone the repository and copy the agent .md definitions into ~/.claude/agents (or .claude/agents inside a project).
  2. Start a new Claude Code session to load the agents.
  3. Delegate work to them with the Task/Agent tool or by name.

Nota editorial

Continuous Claude is a context management and agent orchestration framework built on top of Claude Code that addresses the platform's context compaction problem, where accumulated conversation history is collapsed and nuanced session decisions are lost. It does this through three interlocking systems: 109 natural-language-triggered skills, 32 specialized subagents (including scout for codebase exploration and oracle for research), and 30 hooks that fire automatically during the Claude Code lifecycle. A YAML-based handoff system transfers state between sessions more token-efficiently than prose summaries, while a background daemon extracts learnings after each session and surfaces them on resumption. The TLDR code analysis layer performs five-pass semantic indexing so Claude reads compressed file representations rather than raw source, reducing token burn. Hooks also run pyright and ruff immediately after edits to catch errors before tests run. Users interact in plain language rather than slash commands, and a hook injects skill-activation suggestions into each message. The system targets developers doing long, multi-session projects in Claude Code who need compounding institutional memory rather than perpetual cold starts.

Items instalables

24 items en este repositorio

aegisSubagent

Security vulnerability analysis and testing

Instalar
agent-context-isolationSkill

Agent Context Isolation

Instalar
agent-orchestrationSkill

Agent Orchestration Rules

Instalar
agentic-workflowSkill

Agentic Workflow Pattern

Instalar
agentica-agentSubagent

Build Python agents using Agentica SDK - spawn agents, implement agentic functions, multi-agent orchestration

Instalar
agentica-claude-proxySkill

Guide for integrating Agentica SDK with Claude Code CLI proxy

Instalar
agentica-infrastructureSkill

Reference guide for Agentica multi-agent infrastructure APIs

Instalar
agentica-promptsSkill

Write reliable prompts for Agentica/REPL agents that avoid LLM instruction ambiguity

Instalar
agentica-sdkSkill

Build Python agents with Agentica SDK - @agentic decorator, spawn(), persistence, MCP integration

Instalar
agentica-serverSkill

Agentica server + Claude proxy setup - architecture, startup sequence, debugging

Instalar
agentica-spawnSkill

Spawn Agentica multi-agent patterns

Instalar
arbiterSubagent

Unit and integration test execution and validation

Instalar
architectSubagent

Feature planning, design documentation, AND integration planning

Instalar
ast-grep-findSkill

AST-based code search and refactoring via ast-grep MCP

Instalar
async-repl-protocolSkill

Async REPL Protocol

Instalar
atlasSubagent

End-to-end and acceptance test execution

Instalar
background-agent-pingsSkill

Background Agent Pings

Instalar
braintrust-analystSubagent

Analyze Claude Code sessions using Braintrust logs

Instalar
braintrust-analyzeSkill

Analyze Claude Code sessions via Braintrust

Instalar
braintrust-tracingSkill

Braintrust tracing for Claude Code - hook architecture, sub-agent correlation, debugging

Instalar
buildSkill

Workflow orchestrator that chains existing skills for feature development

Instalar
chroniclerSubagent

Session analysis, precedent lookup, and learning extraction

Instalar
cli-referenceSkill

Claude Code CLI commands, flags, headless mode, and automation patterns

Instalar
commitSkill

Create git commits with user approval and no Claude attribution

Instalar
README

Resumen de Subagents

README no disponible. Visita el repo en GitHub para la documentación completa.
Topics
agentsclaude-codeclaude-code-cliclaude-code-hooksclaude-code-mcpclaude-code-skillsclaude-code-subagentsclaude-skillsmcp
Preguntas frecuentes

Lo que la gente pregunta sobre Continuous-Claude-v3

¿Qué es parcadei/Continuous-Claude-v3?

parcadei/Continuous-Claude-v3 es subagents para el ecosistema de Claude AI. Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows. Tiene 3.9k estrellas en GitHub y su última actualización registrada es del 2026-01-26.

¿Cómo se instala Continuous-Claude-v3?

Puedes instalar Continuous-Claude-v3 clonando el repositorio (https://github.com/parcadei/Continuous-Claude-v3) o siguiendo las instrucciones del README en GitHub. ClaudeWave también te ofrece bloques de instalación rápida en esta misma página.

¿Es seguro usar parcadei/Continuous-Claude-v3?

Nuestro agente de seguridad ha analizado parcadei/Continuous-Claude-v3 y le ha asignado un Trust Score de 77/100 (tier: Trusted). Revisa el desglose completo de comprobaciones superadas y flags en esta página.

¿Quién mantiene parcadei/Continuous-Claude-v3?

parcadei/Continuous-Claude-v3 es mantenido por parcadei. La última actividad registrada en GitHub es del 2026-01-26, con 47 issues abiertos.

¿Hay alternativas a Continuous-Claude-v3?

Sí. En ClaudeWave puedes explorar subagents similares en /categories/agents, ordenados por popularidad o actividad reciente.