Individual skill
codex-model-routing-team
为有净收益的独立子任务安排多模型协作；简单或强顺序任务直接执行。
skills/codex-model-routing-team/SKILL.md
Source commit d09cc28cd0915808534ea3bf199f17efa75553a6
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 10, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 787
- Repository last updated
- Nov 6, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- engineering Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
LICENSEasset · 1,076 bytesSKILL.mdcore · 4,373 bytesagents/interface.yamlasset · 1,150 bytesagents/openai.yamlasset · 341 bytesevals/model-routing-recovery.jsonasset · 5,768 bytesevals/team-planning-semantic-config.jsonasset · 1,619 bytesevals/team-planning-trigger-cases.jsonasset · 1,691 bytesevals/team-planning.jsonasset · 2,116 bytesevals/upstream-skill-integration.jsonasset · 2,372 bytesreferences/audit-schema.jsonasset · 2,808 bytesreferences/cli-audit-schema.jsonasset · 1,090 bytesreferences/durable-mode.mddoc · 1,961 bytesreferences/ephemeral-cli-surface.mddoc · 2,202 bytesreferences/model-registry.jsonasset · 9,745 bytesreferences/native-audit-schema.jsonasset · 3,832 bytesreferences/native-quick-path.mddoc · 2,920 bytesreferences/native-subagent-lifecycle.mddoc · 2,962 bytesreferences/official-multi-agent-v2-evidence.mddoc · 3,346 bytesreferences/provider-policy.mddoc · 5,314 bytesreferences/recovery-policy.mddoc · 8,963 bytesreferences/route-compiler.mddoc · 5,258 bytesreferences/routing-policy.mddoc · 8,609 bytesreferences/surface-selection-policy.mddoc · 3,904 bytesreferences/task-packet.mddoc · 3,754 bytesreferences/team-plan.mddoc · 5,269 bytesreferences/thread-lifecycle.mddoc · 6,199 bytesreferences/thread-supervision-protocol.mddoc · 7,334 bytesreferences/upstream-skill-adapter.mddoc · 5,367 bytesreferences/validation-cases.mddoc · 7,538 bytesscripts/compile_route_plan.pyruns · 37,458 bytesscripts/model_preflight.pyruns · 19,500 bytesscripts/prepare_native_team.pyruns · 5,006 bytesscripts/route_policy.pyruns · 751 bytesscripts/validate_route_plan.pyruns · 26,962 bytesscripts/validate_team_ledger.pyruns · 35,726 bytesscripts/validate_team_plan.pyruns · 18,469 bytestests/test_ephemeral_cli_routing.pyruns · 7,617 bytestests/test_luna_routing.pyruns · 8,609 bytes
Read excerpt
# Codex 模型路由团队
主 Agent 保持模型并负责集成验收；独立执行交给 1–3 个 Worker。两个以上 Worker 先编译 TeamPlan；边界明确且可验收的执行默认 GPT-6 Luna XHigh，复杂执行 Luna Max；未决判断 Sol Medium/High，高风险 Sol High，关键独立审查 Sol XHigh。派遣前声明 `task_contract`：决策是否已定、如何验收；提示词长或文件多不单独触发 Sol。
## 按需选择路径
- 默认原生 Standard、新 standard 团队且单元可共用风险路由：读 [原生简洁路径](references/native-quick-path.md)，用 `scripts/prepare_native_team.py` 一次生成已校验派遣参数和初始账本。
- 路由不同、Fast、单 Worker 或已有团队恢复：读 [编译器接口](references/route-compiler.md)；两个以上 Worker 按 [TeamPlan](references/team-plan.md) 校验，原生执行读 [生命周期](references/native-subagent-lifecycle.md)。
- 需要用户明确要求的持久 Task：核对宿主授权后读 [Thread 生命周期](references/thread-lifecycle.md) 与 [监督协议](references/thread-supervision-protocol.md)。worktree 需求本身不授权创建 Task。
- 用户点名 exact CLI model：读 [CLI Surface](references/ephemeral-cli-surface.md)，核对 help/catalog、授权与 fresh context。
- 上游 Skill 已定义拆分、阶段和产物时，遵守 [适配协议](references/upstream-skill-adapter.md)，不重做阶段门或业务账本。
## 所有路径共用
