Workflows agénticos — Maestría8 / 8
Multi-Tool Pipelines — Ticket to Reviewed Branch
The payoff: chain MCP, hooks, commands and subagents into one flow that takes a ticket to a reviewed branch — with you in the loop only where it counts.
Each building block is useful alone. Chained, they become a pipeline that takes a ticket from "assigned" to "reviewed branch" while you watch the decisions, not the keystrokes.
The flow
- Pull the work — an MCP server fetches the ticket (Linear, Jira, GitHub) so the agent has the real spec, not your paraphrase.
- Plan first — start in
planmode. The agent reads the codebase and proposes an approach. You approve or redirect — the one human gate that matters. - Implement with guardrails — it edits code; a
PostToolUsehook auto-formats every file; aPreToolUsehook blocks anything destructive. - Review by a specialist — a
code-reviewersubagent reads the diff in its own context and reports bugs, security issues, and missing tests. - Ship — a
/open-prcustom command writes the branch, commit, and PR body from the diff.
Wiring it as one command
Package the repeatable part as a slash command so the team runs the same pipeline:
---
description: Take a ticket to a reviewed branch
argument-hint: [ticket-id]
allowed-tools: Read, Edit, Bash(git *:*), mcp__linear__*
---
1. Fetch ticket $1 via the Linear MCP and summarize the spec.
2. Propose a plan and wait for approval.
3. Implement; rely on hooks for formatting and safety.
4. Invoke the code-reviewer subagent on the diff.
5. Open a PR with a summary of changes and the review findings.
Unattended runs
For CI or overnight batches, run headless: claude -p with --output-format json and a strict --allowedTools. The agent never blocks on a prompt — because you set the limits up front.
Serie — Workflows agénticos — Maestría
- Parte 01La mentalidad del flujo de trabajo agénticoLa mayoría de los desarrolladores tratan la IA como un autocompletado más inteligente. Los que avanzan la tratan como un compañero que actúa. Aquí está el modelo mental.
- Parte 02MCP Servers 101 — Dale herramientas reales a tu agenteEl Model Context Protocol es cómo tu agente deja de adivinar y comienza a consultar tu base de datos, tus issues, tu navegador. Aquí está el modelo mental y la primera conexión.
- Parte 03Construye tu primer servidor MCP personalizadoLos servidores predefinidos cubren GitHub y Postgres. El de alto impacto es el servidor que solo tú puedes escribir — el puente hacia tu propio sistema.
- Parte 04Hooks — Make the Agent Obey Your RulesA prompt asks the model to remember. A hook makes it happen — deterministically, every time, outside the model's control.
- Parte 05Custom Slash Commands as Team WorkflowsA custom slash command is a reusable prompt you commit to the repo — so the whole team runs the same high-quality instruction instead of re-typing it.
- Parte 06Subagentes — Delegando Trabajo que EscalaUn contexto gigante se vuelve lento y vago. Los subagentes permiten que el agente principal delegue trabajo enfocado a especialistas con su propio contexto y herramientas — y ejecutarlos en paralelo.
- Parte 07The Daily-Driver Setup — Settings, Permissions, Status LineLa diferencia entre luchar contra el agente y fluir con él es veinte minutos de configuración que haces una sola vez. Aquí está la configuración.
- Parte 08Multi-Tool Pipelines — Ticket to Reviewed Branch — estás aquíThe payoff: chain MCP, hooks, commands and subagents into one flow that takes a ticket to a reviewed branch — with you in the loop only where it counts.