Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zjp1997720/zhijian-skills --skill codex-model-routing-teamgit clone --depth 1 https://github.com/zjp1997720/zhijian-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zjp1997720/zhijian-skills/codex-model-routing-team)<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/codex-model-routing-team"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/codex-model-routing-team/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zjp1997720/zhijian-skills/codex-model-routing-team"><img src="https://agentmods.dev/badge/skills/zjp1997720/zhijian-skills/codex-model-routing-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00030 | $0.01155 |
| Opus 5.5 | $0.00012 | $0.00462 |
| Sonnet 5.5 | $0.00006 | $0.00231 |
| Haiku 4.5 | $0.00003 | $0.00115 |
Grade A, and why
codex-model-routing-team scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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，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；两个以上 Worker 按 TeamPlan 校验，原生执行读 生命周期。
- 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 与 监督协议。worktree 需求本身不授权创建 Task。
- 用户点名 exact CLI model：读 CLI Surface，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，不重做阶段门或业务账本。
所有路径共用
- 自动派遣需 2+ 独立交付物且净收益为正；点名单 Worker 可执行，否则主 Agent 直接完成。
- 编译器读取 registry 并执行 RoutePlan 校验，不省略 Provider、live schema 或数据边界。特殊 Provider/覆盖或失败诊断才展开 Provider、路由、Surface；不用每次先读齐。
- 派遣前明确 unit、唯一 task_id、权限、精确所有权和验收；完整 任务包 仅在输入/上下文/权限复杂时展开。主 Agent 保持集成和最终验收。
- 默认
standard6/8/3，实际受 live child slots 及更严的用户上限约束；expanded12/16/6 仅按 TeamPlan 容量门启用。每 unit 最多 2 次 attempt、一次 follow-up；失败只沿 预声明链。 - 结果经主 Agent 验证后采纳，正式状态确认收口并运行
scripts/validate_team_ledger.py。编译准备不等于已执行，不把创建回执当完成。
硬门
- registry 决定范围；live schema 只证明当前 host 接受精确组合。requested/accepted/observed 分开记录，未回显为
unknown。 - GPT-6.1 Sol / GPT-6 Luna 的官方 catalog 均为 V2；本 Skill 将所有 Worker 限制为叶子执行角色，禁止继续派遣。当前 host 必须接受精确模型组合。
- 不加
model: lunafrontmatter；编排入口留在协作父 Agent，Luna 只做 Worker。 - Luna 最低 XHigh；Sol 最低 Medium；Terra 仅显式首项；Grok 过门；Gemini 3.6 blocked。DeepSeek 4.1/Gemini 3.8 仅走 manual/experimental CLI。禁止 Ultra。
- Fast 即
service_tier=priority；live schema 无字段时一律 Standard，不把 catalog 或请求值冒充 observed Fast。 app_thread只用于 worktree、侧栏、跨任务恢复、耐久监督或预声明 fallback，并且必须有 live 能力与宿主授权证据。- Worker 不得继续派生或执行发布、发送、付款、删除、账户、生产变更；主 Agent 不切换模型。
- TeamPlan 不创建 Planner、不调用重型计划、不落持久文件；同波写冲突、依赖环、超预算、计划外 Worker、下放验收必须拒绝。
- 未确认返回值或
pendingWorktreeId不得当正式身份；UNKNOWN禁止追问、归档、fallback、重复创建、改库。
What ships with it
37 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/interface.yaml 1.1 KB
- agents/openai.yaml 341 B
- evals/model-routing-recovery.json 5.6 KB
- evals/team-planning-semantic-config.json 1.6 KB
- evals/team-planning-trigger-cases.json 1.7 KB
- evals/team-planning.json 2.1 KB
- evals/upstream-skill-integration.json 2.3 KB
- LICENSE 1.1 KB
- references/audit-schema.json 2.7 KB
- references/cli-audit-schema.json 1.1 KB
- references/durable-mode.md 1.9 KB
- references/ephemeral-cli-surface.md 2.2 KB
- references/model-registry.json 9.5 KB
- references/native-audit-schema.json 3.7 KB
- references/native-quick-path.md 2.9 KB
- references/native-subagent-lifecycle.md 2.9 KB
- references/official-multi-agent-v2-evidence.md 3.3 KB
- references/provider-policy.md 5.2 KB
- references/recovery-policy.md 8.8 KB
- references/route-compiler.md 5.1 KB
- references/routing-policy.md 8.4 KB
- references/surface-selection-policy.md 3.8 KB
- references/task-packet.md 3.7 KB
- references/team-plan.md 5.1 KB
- references/thread-lifecycle.md 6.1 KB
- references/thread-supervision-protocol.md 7.2 KB
- references/upstream-skill-adapter.md 5.2 KB
- references/validation-cases.md 7.4 KB
- scripts/compile_route_plan.py 37 KB runs code
- scripts/model_preflight.py 19 KB runs code
- scripts/prepare_native_team.py 4.9 KB runs code
- scripts/route_policy.py 751 B runs code
- scripts/validate_route_plan.py 26 KB runs code
- scripts/validate_team_ledger.py 35 KB runs code
- scripts/validate_team_plan.py 18 KB runs code
- tests/test_ephemeral_cli_routing.py 7.4 KB runs code
- tests/test_luna_routing.py 8.4 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · -7 lines · -58 tokens per session 7e5b111116b9
- 2mo ago Changed · +1 lines · -35 tokens per session 6c91cfb2f448
- 2mo ago First seen · 47 lines · 123 tokens per session scan A 9b92fbadc138
codex-model-routing-team is a skill published in the GitHub repository zjp1997720/zhijian-skills (787 stars, last pushed 4d ago), licensed MIT. It adds 30 tokens to every session and 1,155 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
codex-model-routing-team compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| codex-model-routing-teamzjp1997720/zhijian-skills | Skill | 787 | 4d ago | MIT | A | 30 | Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |