codex-model-routing-team

Original：🇨🇳 Chinese

Translated

5 scripts

Compile TeamPlan for tasks with clear net parallel benefits. By default, use Codex native Multi-Agent V2 to create Luna XHigh/Max leaf Workers, and switch to App Thread when independent worktree, sidebar visibility, cross-task recovery, or durable supervision is required. Applicable for tasks with two or more independent deliverables, independent validation, or when users explicitly request model routing, background Workers, Agents Team, Grok/Gemini Workers. Simple Q&A, status queries, small single-file modifications, strongly sequential tasks, and irreversible operations will not trigger automatically.

1installs

Sourcezjp1997720/zhijian-skills

Added on2026-09-02

NPX Install

npx skill4agent add zjp1997720/zhijian-skills codex-model-routing-team

SKILL.md Content (Chinese)

View Translation Comparison →

Codex Model Routing Team

The main Agent retains the current model and is responsible for task splitting, ownership, integration, and final acceptance. For tasks requiring two or more Workers, compile TeamPlan first; the default routing is

native_subagent/gpt-5.6-luna/xhigh/standard

, and upgrade to

max

for high-risk tasks. App Thread is a dedicated Surface for stateful workspaces and durable tasks, and is no longer a compatibility entry for Luna.

Do Not Use

Simple Q&A, status queries, small single-file modifications, strongly sequential tasks, and irreversible external operations remain in the main task; Workers can only prepare materials for external actions.

Execution Modes

```
native-v2
```
(default): Use native V2 to create Luna leaf Workers; use
```
fork_turns="none"
```
for fresh context, and write a positive integer when a small amount of recent context is needed. Three types of JSON are validated from stdin by default.
```
durable-app
```
: Use App Thread and durable ledger when the task requires independent worktree, sidebar visibility, cross-task recovery, long-term supervision, or when the native path lacks precise live capabilities.
When the upstream Skill has defined splitting, phases, and deliverables, comply with the Adapter Protocol and do not rework Scale, phase gates, or a second set of business ledgers.

Execution Process

Confirm explicit or long-term authorization; dispatch only when there are two or more independent deliverables with positive net benefits, otherwise use
```
lead_only
```
.
For two or more Workers, compile unit, dependencies, ownership, deliverables, acceptance, and integration sequence according to the TeamPlan Protocol, and run
```
scripts/validate_team_plan.py
```
; only compile without rewriting when an upstream plan already exists.
Fix the candidate chain according to registry, Provider, Routing and Surface Selection strategies.
Generate
```
schema_version: "3.0"
```
RoutePlan for each unit, write
```
surface_intent: parent_integrated|durable_app
```
and run
```
scripts/validate_route_plan.py
```
. Native candidates must explicitly write
```
fork_turns
```
and tuple-bound
```
runtime_evidence
```
; Fast must also have current live
```
service_tier=priority
```
evidence.
The Task Packet includes unit, unique
```
task_id
```
, permissions, acceptance criteria, and prohibits subordinate dispatch; the briefing specifies precise routing, responsibilities, fallback, and reserved slots.
Native path complies with Lifecycle; App path complies with Thread Lifecycle and Supervision Protocol.
TeamPlan uses
```
standard
```
6/8/3 by default;
```
expanded
```
12/16/6 requires live capacity gate, 2 reserved slots, and structured evidence within 10 minutes. Child slots equal total slots minus coordinator and active Workers, and split waves by the smaller value.
Each unit allows a maximum of 2 attempts and 1 follow-up; failure only follows the Pre-declared Chain. Revise TeamPlan only after收口（这里应该是“conclusion”？不对，原文是“收口后”，应该是“after conclusion”？不，看原文是“结构变化才在收口后修订 TeamPlan”，翻译成“Revise TeamPlan only after conclusion when structural changes occur.”）
The main Agent validates integration; after native Workers close or enter completed-idle state according to live capabilities, write
```
RELEASED
```
; archive App Thread after passing the gate. Run
```
scripts/validate_team_ledger.py
```
.

Hard Gates

Registry determines the scope of strategies; live schema only proves that the current host accepts the exact combination. Record requested/accepted/observed separately, and mark unechoed items as
```
unknown
```
.
V2 parent Agent can create V1 leaf models that are visible to picker and not disabled; Luna can use native V2 but does not get collaboration tools. Sol/Terra also prohibit subordinate dispatch.
Do not add
```
model: luna
```
frontmatter; the orchestration entry remains in the collaborative parent Agent, and Luna only acts as a Worker.
Luna requires at least XHigh, Max for high-risk tasks; Sol requires at least High; Terra only for explicit first items; Grok requires passing gates; Gemini is blocked. Prohibit old models, Ultra, and low-intensity fallback.
Fast means
```
service_tier=priority
```
; if there is no such field in the live schema, use Standard uniformly, and do not pass off catalog or requested values as observed Fast.
```
app_thread
```
is only used for worktree, sidebar, cross-task recovery, durable supervision, or pre-declared fallback.
Workers shall not continue to derive tasks, nor execute release, send, payment, deletion, account, or production changes. The main Agent shall not switch its own model.
TeamPlan does not create Planner, call heavy planning, or write persistent files by default; must reject same-wave write conflicts, dependency loops, over-budget, unplanned Workers, or delegated final acceptance.
Do not treat unconfirmed return values or
```
pendingWorktreeId
```
as official identity;
```
UNKNOWN
```
prohibits follow-up questions, archiving, fallback, repeated creation, or database modification.

Output Contract

Deliverables must be complete, self-consistent, and verified by the main Agent, including auditable Surface, model, inference intensity, speed, context scope, Provider gates, attempts, fallback, adoption, and closing status. See Validation Cases and

evals/

for behavioral boundaries.