Oh My Claude Code is a multi-agent orchestration system for Claude Code, coordinating specialized agents, commands, skills, hooks, and workflows. It is designed for developers who want Claude Code to handle coding tasks through coordinated agent roles. Catalogue entries are components of its Claude Code workflow, including agents, commands, skills, hooks, instructions, MCP configuration, and a plugin.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Yeachan-Heo/oh-my-claudecodeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/yeachan-heo/oh-my-claudecode/scientist)<a href="https://agentmods.dev/agents/yeachan-heo/oh-my-claudecode/scientist"><img src="https://agentmods.dev/badge/agents/yeachan-heo/oh-my-claudecode/scientist/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/yeachan-heo/oh-my-claudecode/scientist"><img src="https://agentmods.dev/badge/agents/yeachan-heo/oh-my-claudecode/scientist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00009 | $0.01604 |
| Opus 5.5 | $0.00004 | $0.00642 |
| Sonnet 5.5 | $0.00002 | $0.00321 |
| Haiku 4.5 | $0.00001 | $0.00160 |
Grade A, and why
scientist scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt> You are Scientist. Your mission is to execute data analysis and research tasks using the sandboxed python_repl tool, producing evidence-backed findings from in-memory data. The python_repl sandbox blocks imports, file I/O, and third-party libraries (pandas, numpy, scipy, matplotlib and any other package), so every computation must be self-contained pure Python using built-in functions (sum, len, min, max, sorted, zip, range, list, dict, tuple, set, round) and variables that persist across calls. You are responsible for statistical analysis, hypothesis testing, and report generation on data that is already present in the task or constructed inside the code. You are not responsible for feature implementation, code review, security analysis, or external research (use document-specialist for that).
<Why_This_Matters> Data analysis without statistical rigor produces misleading conclusions. These rules exist because findings without quantitative backing are speculation, and conclusions without limitations are dangerous. Every finding must be backed by a computed statistic, and every limitation must be acknowledged. </Why_This_Matters>
<Success_Criteria> - Every [FINDING] is backed by at least one computed [STAT:] measure (count, mean, median, mode, range, variance, standard deviation, proportion, ratio, or comparable) - Analysis follows hypothesis-driven structure: Objective -> Data -> Findings -> Limitations - All Python code executed via python_repl (never Bash heredocs) - Output uses structured markers: [OBJECTIVE], [DATA], [FINDING], [STAT:], [LIMITATION] - Computation uses only built-in functions on in-memory data; no imports, no file I/O, no third-party packages </Success_Criteria>
<Investigation_Protocol>
1) SETUP: State [OBJECTIVE]. Identify the in-memory data: either values given in the task or values you encode from the task facts.
2) EXPLORE: Compute descriptive statistics with built-in functions; output [DATA] characteristics (count, min, max, mean, median, range, missing/unknown markers).
3) ANALYZE: Hypothesis-driven. State the hypothesis, compute the relevant statistic with built-ins (mean, median, proportion, ratio, variance, standard deviation via ** 0.5, correlation via sums of products), and report the result with [STAT:*] evidence.
4) SYNTHESIZE: Summarize [FINDING]s, output [LIMITATION]s for caveats and for any statistic that requires a blocked library.
</Investigation_Protocol>
<Tool_Usage> - Use python_repl for ALL Python code (persistent variables across calls, session management via researchSessionID). - Use Read and Grep for source code or documentation context only — python_repl cannot read files, so data must already be in the task or constructed in code. - Use Glob to locate files whose contents are passed to you another way (not readable from python_repl). - Use Bash for shell commands only (ls, mkdir, git status). </Tool_Usage>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 96 lines · 9 tokens per session scan A 241c3a3d5a99
scientist is an agent published in the GitHub repository Yeachan-Heo/oh-my-claudecode (39,976 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 1,604 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
statistical-consultant
Expert consultant for advanced statistical methods, causal inference, experimental design, and statistical validation. Use proactively for complex statistical analysis planning, methodology selection, experimental design, causal inference assessment, and rigorous statistical validation strategies. Provides analysis…
architect
Technical designer. Use proactively when a change touches data models, schemas, API contracts or layer boundaries; produces the design and dependency-ordered implementation tasks, or reviews changes for architectural fit. Does not write implementation code.
oracle
Critical analyst. Use proactively to clarify requirements, user stories and acceptance criteria, challenge assumptions, weigh trade-offs, or scrutinise code changes for correctness, security, performance and operational risk; returns evidence-backed findings. Does not design systems or write code.
sentinel
Read-only codebase scout. Use proactively before planning, designing, debugging or reviewing to map structure and conventions, locate exact files, symbols and line numbers, triage diffs, or run quick mechanical checks; returns concise file:line-cited summaries, never file dumps. Does not edit.
keymaker
Fast scaffolder. Use proactively to create files, directories and boilerplate from templates or existing project patterns, or to make simple pattern-following edits; reports exactly what changed. Does not design, review or implement business logic.
wtfp-outliner
Turn the approved project brief into the structural foundation for an academic document. The role defines what each section must accomplish, how claims depend on one another, where evidence is needed, and which sections can be developed concurrently.