code-yeongyu/oh-my-openagent / packages/omo-codex/plugin/components/teammode/skills/teammode
teammode
VerifiedCodex-only team orchestration: run a named team of cooperating Codex workers with durable, script-managed state. MUST USE when the user asks Codex to create, run, coordinate, inspect, archive, or delete a team of agents/threads/sessions, or to work on something as a team in parallel. FIRST inspects the active tool surface (checking tool_search for deferred tools) and tells the user the route: native MultiAgentV2 agents (flat spawn_agent with task_name) when available, Codex App threads as the fallback, or a plain-subagent split when neither set exists. The main session is always the leader; members are defined by a concrete part, ownership area, or perspective - never a vague job role; a bundled cross-platform script writes the .omo/teams state plus an auto-generated member field manual. Use a team when the work is not perfectly isolated but parallelizing helps; use plain subagents when scope is perfectly isolated or the goal is ambiguous. Triggers: team mode, teammode, make a team, run as a team, team of agents, coordinate threads, parallel Codex threads, archive the team.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.7 KB |
| scripts/team-guide.mjs | script | 11.2 KB |
| scripts/team-state.mjs | script | 18.9 KB |
| scripts/team-transport.mjs | script | 2.2 KB |
| scripts/team-worktree.mjs | script | 4.8 KB |
| scripts/team.mjs | script | 15.9 KB |
scripts/team-transport.mjs
View on GitHub// team-transport.mjs - the single source of transport identity for teammode state.
//
// A team runs on exactly ONE transport, chosen at init and immutable afterwards:
// - "multi_agent_v2": members are native Codex MultiAgentV2 agents addressed by task
// name / canonical agent path (`/root/<task_name>`), messaged with flat `send_message`
// and `followup_task`.
// - "codex_app": members are durable Codex App threads addressed by thread id, messaged
// with `codex_app.send_message_to_thread` (the fallback when flat V2 tools are absent).
//
// Zero external dependencies (node builtins only), same portability contract as the
// sibling scripts.
export const TEAM_SCHEMA_VERSION = 3
export const TEAM_TRANSPORTS = ["multi_agent_v2", "codex_app"]
export const DEFAULT_TEAM_TRANSPORT = "codex_app"
export const LEADER_AGENT_PATH = "/root"
// Codex validates V2 task names as lowercase letters, digits, and underscores; "root" is
// the leader's own path segment and can never name a member.
const TASK_NAME_PATTERN = /^[a-z0-9_]+$/
export function parseTeamTransport(value = DEFAULT_TEAM_TRANSPORT) {
if (!TEAM_TRANSPORTS.includes(value)) {
throw new Error(`invalid transport "${value}" - use one of: ${TEAM_TRANSPORTS.join(", ")}`)
}
return value
}
export function isMultiAgentV2(team) {
return team?.transport === "multi_agent_v2"
}
export function isCodexApp(team) {
return team?.transport === "codex_app"
}
export function assertTransport(team, transport, operation) {
if (team?.transport !== transport) {
throw new Error(`${operation} is only valid on ${transport} teams; this team's transport is "${team?.transport}"`)
}
}
export function parseTaskName(taskName) {
const trimmed = typeof taskName === "string" ? taskName.trim() : ""
if (!trimmed) throw new Error("member task name is required on multi_agent_v2 teams (--task-name)")
if (!TASK_NAME_PATTERN.test(trimmed)) {
throw new Error(`invalid task name "${trimmed}" - use lowercase letters, digits, and underscores`)
}
if (trimmed === "root") throw new Error('invalid task name "root" - it names the leader, never a member')
return trimmed
}
export function agentPathForTaskName(taskName) {
return `${LEADER_AGENT_PATH}/${taskName}`
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |