FollowAgents AI AGENTS DIRECTORY
Home / All Agents / Oh My ClaudeCode
Dev & Engineering multi-agent-orchestrationtmux-workerscode-reviewprovider-advisorsautonomous-coding

Oh My ClaudeCode

Team-first multi-agent orchestration for Claude Code, from planning through verification and repair.

View on GitHub ↗ Quick start ↓
Source repo
Yeachan-Heo/oh-my-claudecode
Stars
★ 41k
Last updated
today
License
MIT
Primary language
TypeScript
FA score
63/100 · Some gaps

At a glance

How it runs
Agent plugin / skillCLILibrary / SDK
Works with
Platform-specificClaude CodeCodex · Claude API (Partial support)
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
Claude Code CLIClaude Max/Pro subscription or Anthropic API keytmux for omc team and rate-limit detectionShell / CLINetwork accessLocal filesystem
Typical use
A Claude Code engineering team fixing an authentication flow can use /team to coordinate planning, implementation, verification, and follow-up fixes.
Not a fit if
  • Teams not using Claude Code
  • Teams relying on interactive slash commands in CI
Source review
63/100 · Some gaps

What does this agent do, and when should you use it?

Oh My ClaudeCode (OMC) is a Claude Code plugin and command-line runtime for multi-agent development workflows. Its in-session interfaces include /team, /autopilot, /ralph, /ultrawork, and /deep-interview, while its terminal interfaces include omc setup, omc ask, and omc team. The /team workflow follows team-plan → team-prd → team-exec → team-verify → team-fix, whereas omc team launches selected provider CLIs in tmux panes on demand. OMC stores runtime state, session data, plans, logs, handoffs, and local artifacts under .omc/ by default, with HUD, session summaries, and replay logs for inspection. It fits developers already working in Claude Code who want coordinated planning, execution, verification, and repair rather than a single prompt-response loop.

After installation, users run /setup or /omc-setup inside a Claude Code session, or omc setup from a terminal. /team sends work through the native staged team workflow; /autopilot, /ralph, and /ultrawork provide other in-session execution modes. omc ask <provider> <prompt> invokes a local Claude, Codex, Gemini, Antigravity, Grok, or Cursor CLI and writes a Markdown artifact under .omc/artifacts/ask/. omc team N:<provider> "..." launches the requested CLI workers in the active tmux session; omc team status and omc team shutdown inspect or stop a named team.

  1. A Claude Code engineering team fixing an authentication flow can use /team to coordinate planning, implementation, verification, and follow-up fixes.
  2. A developer who wants independent Codex CLI security review can run omc team 2:codex "review auth module for security issues".
  3. A solo Claude Code user building an end-to-end feature with minimal ceremony can start /autopilot.
  4. A product-minded developer with an underspecified idea can use /deep-interview before implementation to clarify requirements.
  5. An engineering team running headless automation can use deterministic commands such as omc ask and omc session search instead of interactive slash commands.

How do you install or deploy this agent?

Prerequisites: Claude Code CLI plus a Claude Max/Pro subscription or an Anthropic API key. For the recommended plugin route, run these one at a time inside Claude Code:

/plugin marketplace add https://github.com/Yeachan-Heo/oh-my-claudecode
/plugin install oh-my-claudecode

Then run:

/setup

Alternatively, install the npm runtime:

npm i -g oh-my-claude-sisyphus@latest

Then run:

omc setup

Install tmux when using omc team or rate-limit detection.

How do you use this agent?

For a first task inside Claude Code, run:

/autopilot "build a REST API for managing tasks"

For native teams, enable CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in ~/.claude/settings.json, then run:

/team 3:executor "fix all TypeScript errors"

For tmux CLI workers, install and authenticate the selected CLI, enter an active tmux session, then run:

omc team 2:codex "review auth module for security issues"

For a provider advisory artifact, run:

omc ask codex "review this patch"

What are this agent's strengths and limitations?

Pros
  • Provides both an in-session Claude Code team workflow and terminal-launched tmux workers, covering interactive and shell-based execution surfaces.
  • Its documented Team pipeline explicitly separates planning, PRD work, execution, verification, and repair loops.
  • omc ask can invoke several local provider CLIs and persists advisory output as Markdown artifacts under .omc/artifacts/ask/.
  • Local .omc/ state, HUD output, session summaries, replay logs, and friction reports give the workflow inspectable operational artifacts.
Limitations
  • The core product depends on Claude Code; external Codex and other CLI workers do not make it a standalone Codex-native replacement.
  • omc team requires an active tmux session, and each selected provider requires its own installed and authenticated CLI.
  • Named Autopilot stage profiles require Linux and flock; unsupported environments reject explicit --workflow invocations.
  • Interactive slash commands are not appropriate for CI or headless automation; the documented alternative is deterministic terminal commands.

How does this agent compare with similar options?

The repository points Codex CLI users to oh-my-codex for the corresponding orchestration experience, while Oh My ClaudeCode is centered on Claude Code. It names oh-my-opencode as an inspiration, but does not provide an auditable feature-by-feature comparison.

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Oh My ClaudeCode This agent 63 · Some gaps Agent plugin / skillFree + model costs ★ 41k today TypeScript Claude Code
Friday Agent Workbench 68 · Some gaps Desktop appFreemium ★ 46 1d ago TypeScript Codex · Claude Code
Happier 82 · Good Desktop appFree + model costs ★ 2.2k today TypeScript Codex · Claude Code
Harmonist 78 · Good CLIFree + model costs ★ 2.2k 5mo ago Python —

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Some gaps
63/ 100 5-point scale 3.2 / 5
This review covers the source as of Aug 09, 2026. The project has shipped 43 stable release(s) since, which have not been re-reviewed. The score and verdict describe the reviewed version only. Recent releases ↓
Trust 16/29
Reliability 9/14
Adaptability 12/18
Convention 12/18
Effectiveness 9/13
Verifiability 5/8
Why each dimension lost points
Trust16 / 29 · 2.8/5

Evidence shows security configuration (SECURITY.md) and strict mode, but no specific implementation of user confirmation mechanism. Data flow transparency is documented, sensitive data handling has environment variable warnings. Dependency security has version pinning but no vulnerability scan evidence. External effects are documented, rollback mechanism is mentioned but not detailed. Source attribution has author information.

Reliability9 / 14 · 3.2/5

Self-consistency is good, documentation aligns with code. Dependency availability has package.json and CI tests. Failure messages are covered by tests.

Adaptability12 / 18 · 3.3/5

Target audience is clear, scenarios are diverse. Capability boundaries are documented. Trigger words are precise. Environment fit has cross-platform tests.

Convention12 / 18 · 3.3/5

Information architecture is clear, install notes are detailed. Naming is stable. Examples and FAQ are provided. Known limitations are documented. License is clear. Versioning has CI checks. Maintenance responsibility has author and contributing guide.

Effectiveness9 / 13 · 3.5/5

Output usability has documentation and examples. Marginal value is high, providing multi-agent orchestration. Cost-benefit has cost optimization notes.

Verifiability5 / 8 · 3.1/5

Claims are traceable, supported by documentation and code. Cross-source verification has tests. Fact and inference separation is good.

Risks and how to mitigate them
  • Publisher identity is unverified, use with caution.
  • Dependency security lacks vulnerability scan evidence, consider checking dependency versions.
  • User confirmation mechanism is not explicitly implemented, be aware of auto-approval risks.
Evidence confidence: Low Reviewed Aug 09, 2026 Reviewed revision 41a4c0f77144 New commits since this review; the score may not cover them
Review evidence README.de.mdLICENSESECURITY.mdpackage.jsonworkflows/auto-label.ymlworkflows/ci.ymltests/test-jira-provider.shtests/test-psm-prompt-injection.sh
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/oh-my-claudecode.svg)](https://followagents.com/en/agents/oh-my-claudecode)
<a href="https://followagents.com/en/agents/oh-my-claudecode"><img src="https://followagents.com/badge/oh-my-claudecode.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v5.7.30
    Release notes excerpt
    oh-my-claudecode v5.7.30: Fix Windows executable search in project folder Release Notes This release fixes a security issue where omc processes on Windows could inadvertently run executables planted in the project folder. Bug Fixes - fix: stop omc processes on Windows from running executables planted in the project folder (#4768) Stats - 1 PR merged | 0 new features | 1 bug fix | 0 test improvements | 0 chore Install / Update …
    View on GitHub ↗
  2. v5.7.29
    Release notes excerpt
    oh-my-claudecode v5.7.29: Windows provider resolution and state-lock contention fixes Release Notes This release resolves Windows-specific provider resolution issues for both npm-installed and planted-cwd binaries, fixes state-lock contention from early probe attempts, and improves SessionEnd action claim and manifest handling. Note: v5.7.28 was cut from the wrong branch (main instead of dev) and contained only a version bump with no functionality changes; it was not published to npm or GitHub releases. This release incorporates all intended fixes from the 5.7.27→5.7.28→5.7.29 sequence. …
    View on GitHub ↗
  3. v5.7.27
    Release notes excerpt
    oh-my-claudecode v5.7.27: SQLITE_BUSY retry, BigInt file identities, and SessionEnd manifest drift handling Release Notes This release introduces compatibility improvements for NTFS file systems with BigInt inode support, adds retry logic for early SQLITE_BUSY errors during state-lock setup, and improves SessionEnd action claim handling to prevent zombie claims. Thanks to the maintainers for #4717, #4719, #4721, and #4723. Bug Fixes - fix(lib): retry an early SQLITE_BUSY from state-lock database setup (#4717) - fix(utils): use BigInt inodes for NTFS compatibility (#4719) …
    View on GitHub ↗

FAQ

Do I need Codex, Gemini, or another external CLI?
No. OMC is documented as working without optional external providers. You need a provider CLI only when selecting that provider through omc ask or omc team.
What happens if Claude Code native teams are disabled?
OMC warns and falls back to non-team execution where possible. Native teams are enabled with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in Claude Code settings.
What does OMC write into my repository?
It writes runtime state, session data, plans, logs, handoffs, research notes, and local artifacts under .omc/ by default. Only .omc/skills/** is intended to remain committable for shared project skills.
Can I use it in CI?
Use deterministic terminal commands such as omc setup, omc ask, omc session search, and repository scripts, with ANTHROPIC_API_KEY or provider-specific CLI authentication in the runner. Do not rely on interactive /autopilot, /ralph, or /team commands.
View on GitHub ↗ Install ↓

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Open Source Coding Agents, Compared

Open source coding agents ranked by FARS review — score, trust, license, language and maintenance side by side, with what each one is and isn't good at.

Claude Code Agents, Compared

Claude Code agents ranked by FARS review — compatibility is read from each agent's own AGENTS.md and documentation, not assumed, and only full support is listed.

Related agents

Dev & Engineering

Friday Agent Workbench

Coordinate local coding agents to split work, communicate, and hand off tasks when a tool reaches its usage limit.
Dev & Engineering

Happier

Control, review, and ship work from multiple coding agents across all your devices.
Dev & Engineering

Harmonist

An IDE-hooked multi-agent workflow that enforces review, memory, and integrity checks for AI-assisted coding.
Dev & Engineering

Maestro Orchestration Platform

Multi-agent development orchestration for Gemini CLI, Claude Code, Codex, and Qwen Code: 39 specialists, parallel subagents, persistent sessions, and built-in review, security, SEO, accessibility, and compliance tooling.