Back to Agents & Commands
Hook

test-runner

Automatically run relevant tests after code changes. Detects test files and runs appropriate test commands based on file extensions and project structure.

test-runner is a Claude Code hook you can drop into a project. It plugs into the Claude Code workflow directly, so it is useful when a task keeps recurring and you want it handled the same way each time.

Everything on this page — the summary, the category and the how-to — is written by HowToPrompts; the link below goes to the original project.

TypeHook
/hook add test-runner

How to use it

  1. Add the file to `.claude/agents/` (subagent) or `.claude/commands/` in your project.
  2. Restart Claude Code so it registers the new entry.
  3. Invoke it by name, or let the main session delegate to it.
Compiled and written by HowToPrompts from public sources.

Related in Hook

prompt · submitRuns the instant you hit enter — it can vet, log or inject context before Claude ever sees the prompt.tool · pre-useFires before any tool runs, so it can screen or block risky calls like rm -rf or .env reads first.tool · post-useRuns the moment a tool finishes and turns the raw result into clean, logged output.notifyPicks up Claude's 'waiting on you' pings and can surface them as a desktop or voice alert.turn · stopFires when a turn wraps — ideal for a spoken or written 'all done' summary.subagent · stopMarks the moment a delegated subagent finishes its task and hands control back.context · pre-compactRuns just before the context window is compacted, so it can back the transcript up first.session · startLoads your working context — git status, open issues, notes — the second a session opens.session · endCleans up on exit: logs the session and clears temp files and stale logs.permission · requestSits on the approval dialog and can auto-allow safe read-only actions or audit the rest.
← Back to Agents & Commands