code-yeongyu/lazycodex/teammode

Teammode

Run a named team of cooperating Codex workers under one leader, with durable state on disk. This is a Codex-only workflow. It never depends on an external terminal runner - it coordinates through Codex's own collaboration tools plus a bundled state script, on ONE of two transports chosen up front: native MultiAgentV2 agents, or Codex App threads as the fallback.

When to use a team (and when to use plain subagents instead)

Use a TEAM when EITHER holds:

• the work does NOT split into perfectly isolated pieces, but doing it in parallel is clearly

more convenient - members will need to see and react to each other's findings; or

• one task still needs exploration, yet its GOAL is already clear - parallel investigation under

a fixed objective.

Use plain fire-and-forget subagents ($ulw / one-off spawn_agent workers) - NOT a team - when EITHER holds:

• the work IS perfectly isolated, so there is no coordination cost worth paying; or
• the GOAL is still ambiguous, where one mind should resolve direction before any fan-out.

A team buys cross-member coordination at a real overhead cost; only spend it when coordination is the thing you actually need.

Pick the transport FIRST - then tell the user

Before creating any team state, decide which transport this session can run. Inspect your active tool list and select:

1. MultiAgentV2 (preferred) - select when the flat V2 collaboration tools are ALL active:

flat spawn_agent whose schema requires task_name, plus send_message, followup_task, wait_agent, list_agents, and interrupt_agent. Members are durable native agents addressed by task name / agent path (/root/<task_name>). The namespaced multi_agent_v1.* surface never qualifies as a team transport.

1. Codex App threads (fallback) - select when flat V2 is not available but the

codex_app.* thread tools are (create_thread, read_thread, send_message_to_thread, set_thread_title, set_thread_archived).

1. Neither set visible - if a tool_search tool is active, search for the missing sets

(e.g. spawn_agent, codex_app) before concluding: some environments defer tools behind tool search. A hit is only a lead: revalidate that the visible result is the COMPLETE, mutually compatible transport set from case 1 or 2 before selecting it. Do not combine partial hits from different transports.

1. Neither set exists - teammode cannot run here. Do NOT run init or fake a team with

partial tooling. If another visible plain-subagent mechanism can independently spawn, communicate with, and observe plain workers, announce that exact mechanism and use it for non-overlapping scopes. Otherwise continue serially and report the capability limitation; never promise or imply plain subagents that this session cannot create.

Then, BEFORE running init (or instead of it in case 4), tell the user in one line what this environment provides and which route you picked:

• Teammode transport: MultiAgentV2 (flat spawn_agent with task_name).
• Teammode transport: Codex App threads (flat V2 tools not present in this session).
• `Teammode unavailable: neither MultiAgentV2 nor codex_app tools exist in this session -

using <visible plain-subagent mechanism> for independent scopes.`

• `Teammode unavailable: neither MultiAgentV2 nor codex_app tools exist in this session, and

no compatible plain-subagent mechanism is available - continuing serially.`

Pass the choice to init as --transport multi_agent_v2 or --transport codex_app. The transport is recorded in team.json and is IMMUTABLE for the team's lifetime: a V2 spawn failure is a V2 blocker to report, never permission to mix Codex App threads into the same team. Never probe by trial-calling tools; read your tool list, and search it with tool_search only when a needed set is not visible.

You are the leader - orchestrate, do not implement

The main session is ALWAYS the team leader; you orchestrate directly and never spin up a separate leader worker. Your job is orchestration, NOT writing product code: split the work and assign each slice, hold live situational awareness of every member, verify and QA what they deliver, relay findings between members, instruct and unblock, and synthesize the result. DELEGATE every code edit to a member - if you catch yourself editing product files while the team runs, that work was a member's slice you should have handed off. You own direction, verification, and integration (the merge), not the keystrokes.

Compose by part, ownership, or perspective - not by job title

A team is ALWAYS two or more members - never a single-member team. One worker on an isolated job is a plain subagent, not a team; if you end up with a single member, either split off a second distinct slice or drop the team and use a subagent.

Compose the team from what you actually KNOW about the work. Ground the split in real knowledge of the problem, then divide it into clear, non-overlapping responsibilities - one per aspect of the work - and give each member exactly one. No two members may own the same thing. Define each member by a concrete slice: a specific part of the codebase, an ownership area, or a distinct perspective/lens. Assigning a vague role ("backend dev", "release analyst", "the tester") is an anti-pattern - it gives the member no real boundary and invites overlap. Each member's focus names what they own concretely; the lens is one of area, ownership, or perspective. Give each member a short, distinct --name too - its role or what it watches (e.g. app-server-lifecycle, mailbox-delivery) - it labels the member everywhere; never reuse one name for two members. On MultiAgentV2 teams also give each member a unique --task-name in lowercase_digits_underscores form - it becomes the member's permanent agent path /root/<task_name>.

Run the script - never hand-write team state

A bundled, dependency-free Node script owns all team state so you never author team.json or the member manual by hand. Run it with node (or bun); it works on macOS, Linux, and Windows. Replace <skill-root> with this skill's own directory.

node "<skill-root>/scripts/team.mjs" init        --name "<team>" --session-name "<session>" --transport multi_agent_v2|codex_app [--session <leader_thread_id>] [--worktree] [--base-branch dev]
node "<skill-root>/scripts/team.mjs" add-member  --team <session_id> --id A --name "<short role>" [--task-name <v2_task_name>] --focus "<part/ownership/perspective>" --lens area|ownership|perspective --deliverable "<...>" [--branch <branch>]
node "<skill-root>/scripts/team.mjs" bind-agent   --team <session_id> --id A --agent-path /root/<task_name> [--cwd <path>]   # multi_agent_v2 teams
node "<skill-root>/scripts/team.mjs" bind-thread  --team <session_id> --id A --thread <thread_id> [--cwd <path>]             # codex_app teams
node "<skill-root>/scripts/team.mjs" member-prompt --team <session_id> --id A
node "<skill-root>/scripts/team.mjs" set-status   --team <session_id> --id A --status reported|blocked|active|archived [--note "<...>"]
node "<skill-root>/scripts/team.mjs" worktree-add    --team <session_id> --id A [--base-branch <branch>]
node "<skill-root>/scripts/team.mjs" worktree-remove --team <session_id> --id A [--force]
node "<skill-root>/scripts/team.mjs" integrate       --team <session_id> [--id A]
node "<skill-root>/scripts/team.mjs" archive      --team <session_id> [--id A] [--note "<...>"]
node "<skill-root>/scripts/team.mjs" delete       --team <session_id> [--force]
node "<skill-root>/scripts/team.mjs" status       --team <session_id>

init creates .omo/teams/{session_id}/ containing team.json (the single durable state file: team id, transport, the main-session leader, the member roster, status, worktree config, and a lifecycle log), guide.md (the auto-generated member field manual), and artifacts/ (a shared exchange space). On codex_app teams {session_id} is the leader's Codex session id when you can pass it via --session; otherwise the script generates a stable handle. Re-running init is a safe no-op. Every mutating subcommand rewrites guide.md, so the manual always matches the current team.

Mutating subcommands take a per-team state lock before reading and rewriting team.json. It is safe to run independent add-member, bind-agent, bind-thread, set-status, archive, delete, guide, and worktree mutation commands concurrently against the same team: they serialize and each command reads the latest committed state before writing. If a command reports that team state is locked, do not treat the intended mutation as complete; retry after the named command finishes, or inspect .omo/teams/{session_id}/.team.lock/owner.json if the previous command crashed. bind-agent refuses codex_app teams and bind-thread refuses multi_agent_v2 teams, and a refused command never changes team.json.

Create the team and its members

init the team, then add-member once per member. What happens next depends on the transport.

MultiAgentV2 teams:

1. If a member needs an isolated worktree, run worktree-add BEFORE spawning it - flat

spawn_agent has no cwd argument, so the path must ride in the bootstrap message.

1. Spawn each member with flat spawn_agent using only the V2 schema fields:

task_name is that member's --task-name, message is the bootstrap printed by add-member / member-prompt, and fork_turns is "none" (members read guide.md for context; full parent history is not their context model). Put any role, priority, or task-specific routing instruction in message; V2 does not accept agent_type, model, reasoning_effort, or service_tier, so members inherit the session model.

1. bind-agent --agent-path with the canonical task name the spawn returned (normally

/root/<task_name>); binding confirms the runtime identity matches the roster and records the member's cwd. Members are durable: they persist as subagent threads, survive idling, and are re-tasked with followup_task - never respawned under a second name.

1. Members appear in list_agents with their task paths; inspect status there instead of

deep links (V2 exposes no thread title or codex:// link surface to you).

Codex App teams:

1. Create a durable thread per member with codex_app.create_thread - ALWAYS this tool for

every member - titled [team name] <member name>, using THAT member's own name, so no two threads share a title. add-member prints the exact title to use. If the tool accepts a working directory / cwd argument, set it to that member's worktree; otherwise the member's manual tells it to cd there first. Use codex_app.set_thread_title if the title did not land at creation. If Codex returns only pendingWorktreeId, the worktree-backed thread is not ready yet: do not bind-thread and do not send the member bootstrap. Wait until Codex surfaces a real threadId, then set the title, bind that real id with the cwd, and only then send the bootstrap.

1. bind-thread to record each thread id (and --cwd), then send that member's bootstrap

trigger as the thread's first message. The trigger is short on purpose: it tells the new thread to READ its guide.md and team.json rather than carrying the whole protocol inline.

1. Whenever you report, audit, reopen, or hand off a member thread, include the app deep link

codex://threads/<thread_id> next to the raw id - worktree-backed threads are easy to lose in the sidebar without it. On a codex_app team, a spawned in-process agent is never a member substitute: it cannot carry the team title or be inspected, titled, archived, or re-opened with the codex_app.* tools this team runs on.