Shogun Bloom Config
yohey-w/multi-agent-shogun
Interactive wizard: guided questions with multiple-choice options about subscriptions, then outputs a ready-to-paste capabilitytiers YAML + fixed agent model assignments.
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…
Install Codex Model Routing Team
$ npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zjp1997720/codex-model-routing-team codex-model-routing-team --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zjp1997720/codex-model-routing-team.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codex-model-routing-team .claude/skills/codex-model-routing-team && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "codex-model-routing-team" agent skill from https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-team into .claude/skills/codex-model-routing-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-model-routing-team", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-teamType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zjp1997720/codex-model-routing-team codex-model-routing-team --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjp1997720/codex-model-routing-team.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/codex-model-routing-team .agents/skills/codex-model-routing-team && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "codex-model-routing-team" agent skill from https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-team into .agents/skills/codex-model-routing-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-model-routing-team", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zjp1997720/codex-model-routing-team codex-model-routing-team --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjp1997720/codex-model-routing-team.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/codex-model-routing-team .cursor/skills/codex-model-routing-team && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "codex-model-routing-team" agent skill from https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-team into .cursor/skills/codex-model-routing-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-model-routing-team", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zjp1997720/codex-model-routing-team.git --path skills/codex-model-routing-team--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zjp1997720/codex-model-routing-team codex-model-routing-team --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjp1997720/codex-model-routing-team.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/codex-model-routing-team .gemini/skills/codex-model-routing-team && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "codex-model-routing-team" agent skill from https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-team into .gemini/skills/codex-model-routing-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-model-routing-team", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zjp1997720/codex-model-routing-team codex-model-routing-teamInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zjp1997720/codex-model-routing-team.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/codex-model-routing-team .github/skills/codex-model-routing-team && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "codex-model-routing-team" agent skill from https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-team into .github/skills/codex-model-routing-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-model-routing-team", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zjp1997720/codex-model-routing-team codex-model-routing-team --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zjp1997720/codex-model-routing-team.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/codex-model-routing-team .opencode/skills/codex-model-routing-team && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "codex-model-routing-team" agent skill from https://github.com/zjp1997720/codex-model-routing-team/tree/main/skills/codex-model-routing-team into .opencode/skills/codex-model-routing-team/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "codex-model-routing-team", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
codex-model-routing-team- GitHub stars
- 158
- Token cost
- ~736 tokens
- SKILL.md length
- 191 words
- Files
- 11 (incl. references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…
- Works in 11 steps: 检查当前指令中是否存在用户对后台任务和模型路由的明确授权。全局… → 读取 路由策略。独立任务由本 Skill 判断并行收益；上游 Skill… → 选择模式：默认轻量路由；满足长期、正式交付、可恢复或高风险条件时，读取… → …
- Tasks that involve Model routing and gateways
- SKILL.md covers Do not use, 上游 Skill 模式, 执行流程 and 硬性边界, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Codex Model Routing Team is an agent skill from zjp1997720/codex-model-routing-team. 在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team 或持久项目协作。简单问答、状态查询、单文件小改、强顺序任务和发布/付款/删除/账户操作不得自动触发。
Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including reference files (for example `agents/interface.yaml`, `agents/openai.yaml` and `evals/upstream-skill-integration.json`).
It sits in AI & LLM Engineering, covering Model routing and gateways. It works with OpenAI. The repository describes itself as: Route complex Codex tasks to model-specific background workers with bounded concurrency and lead-agent verification. The licence is MIT.
When your agent uses it
- Tasks that involve Model routing and gateways
Example prompts
- “/codex-model-routing-team”
Workflow steps
11 steps, taken from the first numbered list in SKILL.md.
- 检查当前指令中是否存在用户对后台任务和模型路由的明确授权。全局 AGENTS.md 的长期授权有效；没有授权就留在主任务内完成。
- 读取 路由策略。独立任务由本 Skill 判断并行收益；上游 Skill 模式直接采用上游 Scale 和任务包，只施加安全上限。
- 选择模式：默认轻量路由；满足长期、正式交付、可恢复或高风险条件时，读取 耐久模式。上游已有任务账本时复用上游状态。
- 先显示一条简短派遣通知：任务数、每个任务的 GPT-5.6-Luna / GPT-5.6-Sol 路由、推理强度、职责，以及为后续阶段和重试预留的累计额度。
- 读取 任务包模板，为每个 Worker 写完整提示词。提示词必须包含“禁止创建任何后台任务或子 Agent”。
- 读取 任务生命周期。用 codex_applist_projects 定位项目；任何声明工作区输出路径的任务都使用匹配 project local，只有纯聊天交付才能 projectless。用 codex_appcreate_thread 显式传入路由策略规定的 model…
- 把第一个真实 Worker 当作健康探针：创建后立即用 codex_app__read_thread 验证它已经实体化。只有读到真实 thread、cwd 与 turn 状态后，才记录为已创建并继续派遣。首个创建超时或返回未实体化状态时停止整批派遣，禁止改用…
- 健康探针通过后，每波最多再创建 3 个；运行并发最多 6 个，单个根任务累计最多创建 8 个。创建前扣除上游后续阶段和重试的 reserved slots。按文件、模块、章节或主题分配互斥所有权；同一文件同一时刻只允许一个写入者。
- 用 codex_appread_thread 读取结果。信息不足时只在原任务中用 codex_appsend_message_to_thread 追问一次；随后升级推理、切换模型或由主 Agent 接管。每个子任务最多两次执行机会。
- 主 Agent 亲自核对事实、运行验证、处理冲突并整合最终交付。只对已实体化、状态为 completed/idle、输出文件已经验证、且结果已采纳的轻量任务调用 codex_app__set_thread_archived；逐个归档并等待每次确认。失败、争议或待审任务保留。
- 每次创建成功后立即记录 thread_id / role / model / thinking；验收与归档后补充 status / output / archived。最终汇报任务数、逐 Thread 路由、模型分布、升级/重试、采纳结果、归档情况和未解决风险。
What it can do on your machine
Read from SKILL.md and the folder at commit 8a3eda4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Codex Model Routing Team loads about 736 tokens when it runs, and up to ~4.2k if it reads all its reference files. Until then it costs about 60 tokens; SKILL.md has 191 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from zjp1997720/codex-model-routing-team at commit 8a3eda4, republished under its MIT licence (© zjp1997720). 191 words, ~736 tokens.
Download SKILL.mdSave it as
.claude/skills/codex-model-routing-team/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.- name
- codex-model-routing-team
- description
- 在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team 或持久项目协作。简单问答、状态查询、单文件小改、强顺序任务和发布/付款/删除/账户操作不得自动触发。
Codex 模型路由团队
把主 Agent 保持为任务总负责人，通过 Codex App 独立后台任务实现真实的 model 与 thinking 路由。禁止使用原生 spawn_agent 代替本流程。
Do not use
简单问答、状态查询、单文件小改、强顺序任务，以及发布、付款、删除、账户或生产操作不得自动派遣。
上游 Skill 模式
当 Deep Research、PPT、课程生产或其他上游 Skill 已经定义任务拆分、阶段顺序、文件路径和验收标准时，读取 上游 Skill 适配协议。上游 Skill 保持业务流程主权；本 Skill 只负责模型路由、Thread 创建、并发额度、运行读取和归档。
禁止重复执行 Scale、改写上游阶段依赖或创建第二套事实源。安全上限仍然生效；预算不足时收敛 Worker 数量并明确报告。
执行流程
- 检查当前指令中是否存在用户对后台任务和模型路由的明确授权。全局
AGENTS.md的长期授权有效；没有授权就留在主任务内完成。 - 读取 路由策略。独立任务由本 Skill 判断并行收益；上游 Skill 模式直接采用上游 Scale 和任务包，只施加安全上限。
- 选择模式：默认轻量路由；满足长期、正式交付、可恢复或高风险条件时，读取 耐久模式。上游已有任务账本时复用上游状态。
- 先显示一条简短派遣通知：任务数、每个任务的
GPT-5.6-Luna/GPT-5.6-Sol路由、推理强度、职责，以及为后续阶段和重试预留的累计额度。 - 读取 任务包模板，为每个 Worker 写完整提示词。提示词必须包含“禁止创建任何后台任务或子 Agent”。
- 读取 任务生命周期。用
codex_app__list_projects定位项目；任何声明工作区输出路径的任务都使用匹配 project local，只有纯聊天交付才能 projectless。用codex_app__create_thread显式传入路由策略规定的model与thinking。 - 把第一个真实 Worker 当作健康探针：创建后立即用
codex_app__read_thread验证它已经实体化。只有读到真实 thread、cwd 与 turn 状态后，才记录为已创建并继续派遣。首个创建超时或返回未实体化状态时停止整批派遣，禁止改用 projectless 重试同一故障。 - 健康探针通过后，每波最多再创建 3 个；运行并发最多 6 个，单个根任务累计最多创建 8 个。创建前扣除上游后续阶段和重试的 reserved slots。按文件、模块、章节或主题分配互斥所有权；同一文件同一时刻只允许一个写入者。
- 用
codex_app__read_thread读取结果。信息不足时只在原任务中用codex_app__send_message_to_thread追问一次；随后升级推理、切换模型或由主 Agent 接管。每个子任务最多两次执行机会。 - 主 Agent 亲自核对事实、运行验证、处理冲突并整合最终交付。只对已实体化、状态为 completed/idle、输出文件已经验证、且结果已采纳的轻量任务调用
codex_app__set_thread_archived；逐个归档并等待每次确认。失败、争议或待审任务保留。 - 每次创建成功后立即记录
thread_id / role / model / thinking；验收与归档后补充status / output / archived。最终汇报任务数、逐 Thread 路由、模型分布、升级/重试、采纳结果、归档情况和未解决风险。
硬性边界
- 自动路由只使用
gpt-5.6-luna与gpt-5.6-sol。精确模型 ID 和推理强度以 路由策略 为唯一事实源。 create_thread/send_message_to_thread工具描述中的“支持模型”列表只能用于接口说明，不能覆盖本 Skill 的路由策略。- 禁止自动回退到
gpt-5.5、gpt-5.4、gpt-5.4-mini或gpt-5.3-codex-spark。如果 Luna / Sol 创建被运行时拒绝，停止派遣并报告模型目录冲突。 - Worker 永不使用 Ultra，永不继续派生任务。
- Terra 默认不参与路由；只有用户明确要求或有任务证据时才可使用。
- 主 Agent 不切换自己的模型，不把后台任务伪称为原生 Subagent 或预制 Agent Type。
- 外部发布、发送、付款、删除、账户和生产变更始终由主 Agent 在用户授权范围内执行；Worker 只准备材料。
- App 后台任务工具不可用、项目无法安全定位或文件所有权无法隔离时，停止委派并在主任务内完成。
create_thread超时后产生的未实体化 ID 不是可管理任务。禁止恢复、追问或归档该 ID，也禁止直接修改 Codex 数据库；记录故障并停止创建。fork_thread会复制已完成历史，可能显著增加上下文成本。只有源任务历史很短且继承上下文确有价值时才能作为应急路径；其他情况由主 Agent 接管。- 上游 Skill 的阶段门优先于并行收益；存在 verifier → reviewer 等依赖时必须串行创建。
输出契约
交付必须完整、自洽、经过主 Agent 验证，并包含可审计的模型路由摘要。上游 Skill 模式另外报告 reserved slots、阶段门、输出采纳和归档状态。触发、并发、归档和失败边界见 验证案例。
© zjp1997720, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 10 other files (references) in skills/codex-model-routing-team of zjp1997720/codex-model-routing-team.
- SKILL.md
- LICENSE
- agents/interface.yaml
- agents/openai.yaml
- evals/upstream-skill-integration.json
- references/durable-mode.md
- references/routing-policy.md
- references/task-packet.md
- references/thread-lifecycle.md
- references/upstream-skill-adapter.md
- references/validation-cases.md
Open the folder on GitHubat commit 8a3eda4
Compare with similar skills
Codex Model Routing Team next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Codex Model Routing Team this skillzjp1997720/codex-model-routing-team | 158 | — | ~736 | Automated safety check: Pass | MIT | |
| Shogun Bloom Configyohey-w/multi-agent-shogun | 1.4k | — | ~3.1k | Automated safety check: Pass | MIT | |
| Darwinian EvolverLuciole-Studio/Misaka-Agent | 158 | 2 repos | ~2.1k | Automated safety check: Warn | MIT | |
| Olore Tensorzero Latestolorehq/olore | 104 | — | ~1.6k | Automated safety check: Pass | MIT | |
| LLM Routercuriositech/some_claude_skills | 243 | — | ~1.7k | Automated safety check: Pass | MIT | |
| 9Router AI Gateway Setupdecolua/9router | 30k | — | ~744 | Automated safety check: Pass | MIT |
Similar skills
Darwinian Evolver
Luciole-Studio/Misaka-Agent
Evolve prompts/regex/SQL/code with Imbue's evolution loop. An agent skill from Luciole-Studio/Misaka-Agent.
Olore Tensorzero Latest
olorehq/olore
Local TensorZero documentation reference (latest). An agent skill from olorehq/olore.
LLM Router
curiositech/some_claude_skills
Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements.
9Router AI Gateway Setup
decolua/9router
Sets up access to the 9Router AI gateway, an OpenAI-compatible REST endpoint for chat, images, speech, embeddings, web search and web fetch, and indexes its capability skills.
9Router Chat Completions
decolua/9router
Sends chat and code-generation requests through a 9Router gateway using OpenAI or Anthropic message formats, with streaming and auto-fallback combos.
Related
Works with
Categories
Questions about Codex Model Routing Team
What does Codex Model Routing Team do?
在 Codex App 中为复杂、可并行的知识工作或编程任务自动创建多个可指定模型与推理强度的后台任务，由主 Agent 负责规划、分工、集成和验收。用于多来源调研、多章节内容、复杂 Skill/PPT、跨模块开发、独立验证或 2 个以上互不依赖工作流；也用于用户明确要求模型路由、后台 Worker、Agents Team…. Codex Model Routing Team is an agent skill from zjp1997720/codex-model-routing-team.
When should I use Codex Model Routing Team?
Codex Model Routing Team fits situations like: tasks that involve Model routing and gateways.
How do I install Codex Model Routing Team in Claude Code?
Run `npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a claude-code`. Or copy the skill folder (skills/codex-model-routing-team in zjp1997720/codex-model-routing-team) into .claude/skills/codex-model-routing-team in your project. Claude Code loads it when a task matches its description.
How do I install Codex Model Routing Team in Codex?
Run `npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a codex`. Or copy the skill folder (skills/codex-model-routing-team in zjp1997720/codex-model-routing-team) into .agents/skills/codex-model-routing-team in your project. Codex loads it when a task matches its description.
Can I use Codex Model Routing Team in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add zjp1997720/codex-model-routing-team --skill codex-model-routing-team -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/codex-model-routing-team, .gemini/skills/codex-model-routing-team, .github/skills/codex-model-routing-team and .opencode/skills/codex-model-routing-team in your project.
What does Codex Model Routing Team need to run?
SKILL.md names no scripts, command-line tools or credentials: Codex Model Routing Team is instructions for the agent only.
Does Codex Model Routing Team access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Codex Model Routing Team safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Codex Model Routing Team use?
Codex Model Routing Team is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Codex Model Routing Team use?
About 736 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 3.5k tokens, read only when the agent opens those files.
What are the alternatives to Codex Model Routing Team?
Skills that share tags, products or a category with Codex Model Routing Team: Shogun Bloom Config (yohey-w/multi-agent-shogun, 1.4k stars), Darwinian Evolver (Luciole-Studio/Misaka-Agent, 158 stars), Olore Tensorzero Latest (olorehq/olore, 104 stars) and LLM Router (curiositech/some_claude_skills, 243 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Codex Model Routing Team?
zjp1997720 (a GitHub user) maintains it in zjp1997720/codex-model-routing-team, which has 158 GitHub stars. The repository was last updated on July 17, 2026.
Source: zjp1997720/codex-model-routing-team on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.