AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Teammode (Codex Team Orchestration)

Runs a named team of cooperating Codex workers under the main session as leader, with durable on-disk team state.

AutomationAdvanced★ 67,531⑂ 5,507AI score 8/10Last updated: Aug 9, 2026

What it does

  • Gives a crisp decision rule for when to form a team versus when to fire off plain subagents (coordination needed vs perfectly isolated scope).
  • Inspects the live tool surface first and locks in one transport - MultiAgentV2 (flat spawn_agent with task_name) or Codex App threads - then announces the chosen route in one line.
  • A bundled dependency-free Node script (scripts/team.mjs) owns all state: .omo/teams/{session_id}/team.json, an auto-generated member manual guide.md, and a shared artifacts/ directory. State is never hand-written.
  • Forces members to be defined by a concrete part, ownership area, or perspective - never a vague job title - and assigns git worktrees whenever two slices would touch the same files.
  • Keeps the leader in orchestration mode (split, verify, relay, integrate) and explicitly bans "any update?" nag pings to working members.
  • Full teardown path: integrate (merge commit) → worktree-remove → archive → delete.

Who it's for

  • Developers running Codex / oh-my-openagent who actually spawn multiple agents.
  • Leads who have been burned by file collisions and duplicated ownership in parallel runs.
  • Anyone executing a ulw-plan document wave-by-wave in parallel.

Examples

  1. "Work on this refactor as a team" → detect transport → init --transport multi_agent_v2 → add-member for three distinct areas → spawn_agent then bind-agent each.
  2. Map wave 1's independent todos from .omo/plans/<slug>.md to one member each; give worktrees only to the two members whose todos overlap in files.
  3. Wrap up with integrate --team <id> for a merge commit, then worktree-remove, archive, and delete to leave no leaked team state.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/code-yeongyu/oh-my-openagent/HEAD/packages/omo-codex/plugin/components/teammode/skills/teammode/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the packages/omo-codex/plugin/components/teammode/skills/teammode folder from the GitHub repo code-yeongyu/oh-my-openagent into my ~/.claude/skills/teammode/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/code-yeongyu/oh-my-openagent.git /tmp/oh-my-openagent && mkdir -p ~/.claude/skills && cp -r /tmp/oh-my-openagent/packages/omo-codex/plugin/components/teammode/skills/teammode ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal in your working directory.
  2. Clone the repo: git clone https://github.com/code-yeongyu/oh-my-openagent.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r oh-my-openagent/packages/omo-codex/plugin/components/teammode/skills/teammode ~/.claude/skills/
  5. Verify the bundled script came along: ls ~/.claude/skills/teammode/scripts/team.mjs
  6. Make sure Node.js (or Bun) is installed: node -v
  7. Restart your session and trigger it with phrases like "team mode", "run this as a team", or "parallel Codex threads".
  8. Note: without MultiAgentV2 or codex_app.* tools in the session, the skill will refuse to create a team and fall back to serial or plain-subagent work.
View source on GitHub ↗License: NOASSERTION