Omg Scientist — Research agent for Claude Code
Read-only analysis/scientist leaf for oh-my-grok ultrabrain slices.
How to install Omg Scientist
Installs to ~/.claude/agents/iml1s-oh-my-grok-omg-scientist.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ImL1s/oh-my-grok/HEAD/agents/omg-scientist.md -o ~/.claude/agents/iml1s-oh-my-grok-omg-scientist.md Restart Claude Code, or start a new session, for it to be picked up.
What Omg Scientist does
name: omg-scientist description: Read-only analysis/scientist leaf for oh-my-grok ultrabrain slices. Evidence first; no edits. promptMode: extend permissionMode: plan capabilityMode: read-only agentsMd: true disallowedTools:
- spawn_subagent
- search_replace
- run_terminal_command
- run_terminal_cmd tools:
- find_by_name
- grep_search
- view_file
- list_dir
- read_url_content
- search_web
omg-scientist — Read-only analyst (leaf)
You are a **depth=1 leaf** scientis
Alternatives in Research
- CLI Explore Agent — Read-only code exploration via Bash + CLI semantic dual-source analysis, with schema-validated structured outp 530 ★
- Digital Forensics And Incident Response Agent — You are a digital forensics and incident response (DFIR) specialist 213 ★
- Writ Explorer — Read-only investigation engine: codebase exploration, auditing, research, and runtime evidence gathering for a 187 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Omg Explore
Read-only codebase mapping for oh-my-grok. Use for quick/explore-high reconnaissance — never edits.
Omg Debugger
Root-cause analysis, regression isolation, stack-trace analysis, and build/compilation error resolution for oh
Pvs Studio
Run PVS-Studio static analysis (SAST + MISRA C:2023 / C++:2008) over a compile_commands.json and report struct
Team Arch Analyst
Read-only deep architecture and code analysis. Cite file:line throughout. Never edits anything. Use when you n
Morty Debater Researcher
Pickle Rick debate researcher. Use when /pickle-debate needs evidence-first analysis of the question.
Errand
Bounded read-only lookup — docs, MCP/skill queries, tool runs, research. Answers, never edits.
Related Skills
Clanker Skills
Evidence-first agent skills for Codex, Claude Code, OpenCode, Pi, and Grok: planning, code review, call-chain
Data Scientist Skills
Ten Claude Code skills that walk an agent through a tabular or time-series ML project without skipping steps.
Pleni
Watch your Claude Code, Codex, Grok and Kimi Code sessions, their sub-agents, and the hand-offs between them,