Omhc Tester — Development agent for Claude Code
Hands-on tester for omhc.
How to install Omhc Tester
Installs to ~/.claude/agents/sungjun1217-oh-my-harness-cowork-omhc-tester.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/SungJun1217/oh-my-harness-cowork/HEAD/.claude/agents/omhc-tester.md -o ~/.claude/agents/sungjun1217-oh-my-harness-cowork-omhc-tester.md Restart Claude Code, or start a new session, for it to be picked up.
What Omhc Tester does
name: omhc-tester description: Hands-on tester for omhc. Use after a change is implemented (and ideally reviewed) to exercise it for real in the isolated sandbox HOME — real Claude Code / Codex CLI sessions launched headless, real hooks, real files — and report what actually happened. Never touches the host HOME or the repo working tree; it reports, it never fixes. tools: Read, Grep, Glob, Bash model: opus
You are the hands-on test agent for omhc (oh-my-harness-cowork). Unit tests and t
Alternatives in Development
- Integration Dev — External API and third-party system integration specialist for Home Assistant, ZoneMinder, weather services, a 849 ★
- Eval Implementer — Implementer role of the D365FO agent eval loop 136 ★
- Evasion — Antivirus and EDR evasion specialist for authorized red team engagements 72 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Kimchi Tester
Hands-on tester for kimchi-claude. Use after a change is implemented (and ideally reviewed) to exercise it for
Omhc Implementer
Implementation specialist for omhc. Use when the change is already understood (ideally after omhc-analyst or a
Backend Reviewer
Use to independently review backend code changes against the backend review checklist and open a draft PR once
Implementer Critical
Implements one high-risk step of an Agentium plan (sandbox and denied paths, money and consent, persistence an
Development360
End-to-end specs-driven delivery agent. Use it when a developer hands over a user story (file or pasted text)
Ralph Tester
Writes tests and runs verification for a Ralph user story that has already been implemented by ralph-coder. Cr
Related Skills
AI Tester
End-to-end behavioral testing skills, bare system prompts, and any agent runtime — run real scenarios in an is
Ccstitch
Local trace store for Claude Code's OpenTelemetry spans: repairs orphaned headless turns (claude-code#99607),
Yologuard
🧩 VS Code extension: Finds AI coding agents launched with permission or sandbox bypass flags where it hurts: