Software Engineering 2026

My Toolkit

The plugins, skills, CLIs, and hooks installed on my laptop, and why each one stays.

This page is mine. The guide tells you how to work with AI agents. Here is the concrete setup I run it on. Everything here is installed on one laptop, around Claude Code as the main agent.

  • Workflow: how a change goes from idea to merged PR, stage by stage.
  • Skills: plugins and skills that change how the agent works.
  • Tools: CLIs, MCP servers, other agents, and the hooks that wire them in.
  • Hot takes: opinions about working with agents, and why I hold them.

How it fits together

LayerJobWhat I usePage
ProcessTake a change from idea to merged PRsuperpowers, /ponytail-review, proving-it-works, no-mistakesWorkflow
BehaviourChange how the agent thinks and talksponytail, caveman, superpowersSkills
ReviewCatch design and code mistakesswe-guidelines, arch-*, grillingSkills
DesignGet from idea to a UI I can point atFigma plugin, ui-ux-pro-max, /mock-optionsSkills
Skill libraryReusable ways of workingpstackSkills
Context saversKeep junk out of the context windowrtk, codegraphTools
GatesStop bad code before it leaves the machineno-mistakes, CodeRabbitTools
Other agentsSecond opinions and local modelsCodex, Cursor agent, OllamaTools
Workspace glueSee what every agent is doingherdr, iTerm status hooks, status lineTools

The rule behind the whole list: a tool earns its place by either saving context or catching a mistake. Anything that does neither gets turned off, because every enabled plugin and skill costs tokens in every session just by being listed.

On this page