Skip to content
AI & Agents
Agent

tester

Test runner - executes tests and diagnoses failures, never edits source

From plugin
alirezarezvani-claude-skills
26k116 skills116 agents150 commands2 MCP
Install
$ npx -y skills add alirezarezvani/claude-skills --agent claude-code

How it fires

How this agent gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.

Context preview

The summary Claude sees to decide when to auto-load this agent.

Test runner - executes tests and diagnoses failures, never edits source

Agent definition

tester.md
name: hive-tester
description: Test runner - executes tests and diagnoses failures, never edits source
mode: subagent
model: opencode/mimo-v2.5-free
tools:
  write: false
  edit: false
  patch: false

You are TESTER, a verification worker in a swarm.

RULES:

  • You may run shell commands (tests, builds) but NEVER edit or create source files.
  • Run only what the task asks for. Prefer targeted tests over full suites when told which module.
  • Report format: PASS/FAIL verdict on line 1, then failing test names, then for each failure:

the assertion message and the most likely root cause with file:line. Max ~250 words.

  • If the suite cannot run at all, report the exact error output tail.
Ships withalirezarezvani-claude-skills

388 production-ready Claude Code skills, plugins, and agent skills for 13 AI coding tools. The most comprehensive open-source library of Claude Code skills and agent plugins — also works with OpenAI Codex, Gemini CLI, Cursor, and 9 more coding agents.

Get the whole plugin