Skip to main content
subagent CX Codex

test-runner · justxor — Claude Code subagent: what it does, how to install

test-runner runs tests on modified files, diagnoses failures, and distinguishes real code bugs from outdated test suites.

MIT ★ 353 updated 2026-10-01

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/test-runner.md
Open on GitHub

What test-runner does

The subagent runs on Claude's haiku model with access to Read, Grep, Glob, and Bash. It automatically discovers test commands by checking CLAUDE.md, package.json, pyproject, or Makefile.

Execution prioritizes tests related to recently modified files before running the full test suite. Rather than dumping raw console output, the agent produces a concise summary with pass and fail counts, failure reasons, and exact file:line locations.

Because execution relies on the Bash tool, your test runner must be functional from the local terminal environment.

What it helps with

  • detect the project test command across configuration files
  • execute targeted tests for modified files first
  • diagnose test failures without reading full terminal logs
  • differentiate genuine code defects from outdated assertions

Example prompts for the agent

  • Run tests on recent code changes and summarize any failures.
  • Check modified files with test-runner and diagnose failed assertions.
  • Inspect test breakage without printing full logs.

How to install test-runner

Manually: put the files in place

.claude/agents/test-runner.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about test-runner

How to install test-runner in Claude Code?

Save the subagent configuration file to .claude/agents/test-runner.md.

What does test-runner do?

It finds your test runner command, tests modified files, and returns a concise summary with failure causes and exact file lines.

Which model and tools does test-runner use?

It operates on the haiku model and relies on the Read, Grep, Glob, and Bash tools.

Source text

test-runner.md · MIT
---
name: test-runner
description: Запускает тесты и анализирует падения. Используй ПРОАКТИВНО после изменений кода, чтобы проверить, что ничего не сломано.
tools: Read, Grep, Glob, Bash
model: haiku
---

Ты специалист по тестам.

1. Определи команду тестов из CLAUDE.md или package.json / pyproject / Makefile.
2. Запусти сначала тесты, относящиеся к изменённым файлам, затем — полный набор, если он быстрый.
3. Для каждого падения: имя теста, суть ошибки (1–2 строки), вероятная причина, файл:строка.
4. Отличай падение из-за бага в коде от падения из-за устаревшего теста.

Верни краткую сводку: X прошло / Y упало, список падений с причинами. Не выводи полный лог.

© justxor · MIT · justxor/claude-code-pro-course

Similar subagents

All subagents for Testing and QA →

test-runner by other authors comes first.

test-runner davila7 test-runner runs project test suites, isolates failure causes, and suggests fixes. The agent never modifies code directly, returning a diagnostic report instead. CX Codex 846installs om-prepare-test-env open-mercato om-prepare-test-env spins up a reproducible local environment for browser QA and tests. It inspects the project stack, builds entrypoint scripts, and saves a shared test descriptor. CX Codex +1 3,900installs cli-review-runner pproenca The cli-review-runner skill for Claude Code checks a CLI command against 45 rules from the cli-for-agents catalog to assess whether an agent can use it safely in a pipeline. CX Codex +1 219installs breakdown-test official github breakdown-test creates test strategies, QA plans, and issue checklists from feature documents. Use it when planning test work for a GitHub project. CX Codex +1 9,264installs qa garrytan qa is a Claude Code skill that tests sites, APIs, and CLIs, then fixes bugs it finds. It responds to requests to test a site or look for errors. CX Codex +1 513installs test-master https://github.com/Jeffallan test-master — a skill that walks an agent through writing unit, integration and E2E tests, reading coverage gaps and tracking down flaky failures. Handy when a project has thin test coverage. CX Codex +1 5,800installs qa-test-planner softaworks Turns a feature description into a test plan, manual test cases, a regression suite or a bug report. Fires only when you name it: qa-test-planner. CX Codex +1 4,400installs

From the same set15

The whole set →
testing testing sets automated test standards for Claude Code: Arrange-Act-Assert structure, banned sleep calls, and strict boundaries for mocks. CX Codex +1 ★ 353repo stars review This skill checks code changes for security issues and exposed secrets, then reports findings with risk levels and file locations. Run it before a merge or when asked for a security review. CX Codex +1 ★ 353repo stars fix-issue fix-issue — a skill that runs the full cycle of fixing a GitHub issue by number — from analysis and test to commit. CX Codex +1 ★ 353repo stars debugger The debugger subagent reproduces errors and failing tests, tracks down their cause, then checks the fix. Use it when a stack trace or unexpected behavior needs investigation. CX Codex ★ 353repo stars docs-writer docs-writer — a subagent that updates README, API docs, code comments, and ADRs whenever your code changes. It verifies actual behavior and keeps examples aligned with reality. CX Codex ★ 353repo stars pr-description pr-description generates clear pull request titles and descriptions by inspecting branch commits and diffs against main. CX Codex +1 ★ 353repo stars architect The architect subagent examines a project before implementation, compares design options, and lays out a change plan. Use it to scope a feature or a major refactor. CX Codex ★ 353repo stars code-reviewer code-reviewer reads your diff, flags security holes, missing tests and edge cases, then returns a severity-sorted report with a file and line for each fix. CX Codex ★ 353repo stars

Project sponsors

Companies that keep this analytics open