How

Use this when you need to understand how a piece of the codebase actually works before changing it. It handles the "how does X work" questions, architecture walkthroughs, and those tricky placement decisions like "which package should own this logic." For simple questions it explores and explains in one pass. For complex subsystems it spawns parallel explorer agents to map different slices (data model, request path, config) then synthesizes their findings into a senior engineer style explanation. The critique mode is interesting: it explains first, then spawns multiple models as independent critics to identify architectural problems. Better than grep and hope, worse than having the original author still around.

skills.sh installs: 6.7K
GitHub stars: 15.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add cursor/plugins --skill how --agent claude-code

Installs into .claude/skills of the current project.

Files

How

Explore the codebase to answer "how does X work?" questions. Produce architectural explanations at the level of a senior engineer onboarding onto a subsystem, enough to build a working mental model, not so much that it reads like annotated source code.

Every spawn is a Task subagent with subagent_type: generalPurpose and readonly: true. Explorers use the how explorer line in the pstack-models.mdc rule (default grok-4.7-xhigh-fast), and every explainer uses the how explainer line (default claude-opus-5-5-xhigh). Set model to that line's value, or to the default if the rule or the line is missing. Leave model unset when the value is auto or inherit-parent. If the Task tool rejects a slug, use the default and say so. If it rejects the default, use the closest valid slug of the same family from its error message. Pick each subagent's reasoning level and fast or standard speed for the job, per the Subagents section of the poteto-mode skill.