Plugin · Claude Code · Productivity

Humanlayer Riptide Rpi

humanlayer-riptide-rpi is a Claude Code plugin for the Build phase that runs a Research–Plan–Implement workflow on Linear tickets before code changes land.

by humanlayer · github.com/humanlayer/riptide-rpi

Run a structured Research–Plan–Implement loop on Linear issues so Claude does not jump straight into code on under-specified tickets.

7
GitHub stars
0
Installs
0
Community votes
One vote per signed-in builder - it helps surface the tools the community actually relies on.
Install

Add it to Claude Code

Install the plugin in Claude Code. One command, paste-ready.

Install the plugin
/plugin install humanlayer-riptide-rpi@humanlayer/riptide-rpi
Add to ClaudeUse the Agent APISkillselion is itself an MCP server - your agent can fetch this config directly.
Agent API

Built to be called by your agent

Skillselion is itself an MCP server. Your agent can pull this entry and a paste-ready install config straight from the API - no copy-paste.

Retrieve this entry with skillselion.get_details("plugin:humanlayer/riptide-rpi") and the paste-ready config with skillselion.get_install_config("plugin:humanlayer/riptide-rpi").

About

What it does

humanlayer-riptide-rpi is a Claude Code plugin that packages the Riptide Research–Plan–Implement workflow for work tracked in Linear. Solo builders and small teams who ship with agents often paste a ticket ID and get a PR before the problem is understood; RPI splits the job into explicit research, a written plan tied to the issue, and implementation only after that gate. The plugin is aimed at indie developers using Claude Code alongside Linear for backlog and delivery, especially when tickets are vague or touch unfamiliar parts of the codebase. It fits the Build phase as ticket-driven PM, but the same ritual applies whenever you open a Linear issue—from scoping in Validate through review in Ship. Install it when you want a repeatable agent methodology instead of one-shot “fix this ticket” prompts. It complements Linear integrations and coding skills by governing how the agent sequences work, not by replacing issue tracking or deployment tooling.

Highlights

  • Research–Plan–Implement (RPI) ritual tuned for Linear tickets
  • Forces context gathering before implementation on agent-driven tasks
  • Aligns agent output with ticket scope instead of ad-hoc coding
  • Workflow plugin (process skill), not a standalone Linear MCP server
  • Single-plugin bundle from humanlayer/riptide-rpi

Why builders use it

Agents rush to patch Linear tickets without reading context, so plans drift and rework piles up on small teams.

Each Linear issue gets a disciplined research and plan phase, then implementation that matches the ticket and approved plan.

At a glance

  • Type - Plugin in Productivity.
  • Adoption - 0 installs, 7 stars, 0 votes.

FAQ

Who is humanlayer-riptide-rpi for?

It is for Claude Code users who manage work in Linear and want Research–Plan–Implement enforced on agent-driven tickets.

When should I use humanlayer-riptide-rpi?

Use it when starting or continuing a Linear issue where jumping straight to code would risk wrong scope, missing context, or unreadable diffs.

How do I add humanlayer-riptide-rpi to my agent?

Register the humanlayer/riptide-rpi Claude Code plugin from the repo, ensure Linear is reachable in your environment, then invoke the RPI workflow against a ticket ID or URL.

Discussion

Comments

Share how you use humanlayer-riptide-rpi, gotchas, or tips for other indie builders.

No comments yet - be the first to share how you use it.

This week for builders

Five minutes, every Monday — the tools, releases and tactics for shipping solo.

unsubscribe anytime.