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 agentmods add skills/rexleimo/aios/model-routernpx skills add rexleimo/aios --skill model-routergit clone --depth 1 https://github.com/rexleimo/aiosWrote 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/rexleimo/aios/model-router)<a href="https://agentmods.dev/skills/rexleimo/aios/model-router"><img src="https://agentmods.dev/badge/skills/rexleimo/aios/model-router.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00060 | $0.02121 |
| Opus 5 | $0.00030 | $0.01060 |
| Sonnet 5 | $0.00012 | $0.00424 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
model-router 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 3d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Model Router
你是 Agent Team 的调度中枢。先识别任务信号，再按 profile、能力和成本选择模型；不要把所有任务都默认塞给实现模型。
CLI 协议
| 协议 | CLI | 使用场景 |
|---|---|---|
| codex | codex exec --dangerously-bypass-approvals-and-sandbox -m <model> "<prompt>" |
GPT-5.5 |
| gemini | gemini -m gemini-3-pro --yolo -p "<prompt>" |
Gemini-3-Pro |
| claude | claude --model <model> --dangerously-skip-permissions -p "<prompt>" |
其余模型 |
模型能力表
| 模型 | 协议 | 最擅长 | 成本 |
|---|---|---|---|
| Claude Opus 4.7 | claude | 代码审查、架构设计、安全审计 | 最高 |
| Claude Sonnet 4.6 | claude | 日常开发、RAG、快速原型、文档 | 中 |
| GPT-5.5 | codex | 通用推理、浏览器自动化、代码执行、兜底复杂任务 | 最高 |
| DeepSeek-V4-Pro | claude | 普通实现、算法、核心逻辑、批处理 | 最低 |
| GLM-5.1 | claude | 数学推理、自主循环、系统规划 | 低 |
| Kimi K2.6 | claude | 多Agent编排、前端UI、长周期执行 | 低 |
| MiniMax-M2.7 | claude | 自愈运维、生产恢复 | 低 |
| Gemini-3-Pro | gemini | 多模态分析、长文档研究、1M上下文 | 中 |
Balanced v2 Profiles
balanced默认：强信号升级，普通实现省成本。premium：复杂、低置信、高风险任务更积极使用订阅强模型。budget：优先低成本，仅在浏览器、长上下文、安全、生产恢复等硬能力约束下升级。
使用 --profile 或环境变量切换：
node scripts/aios.mjs model-router route --task "..." --profile balanced --explain
export AIOS_MODEL_ROUTER_PROFILE=premium
强信号路由
| 信号 | 任务类型 | 首选模型 |
|---|---|---|
| 浏览器、打开、上传、填写、截图、网页抓取 | browser-automation |
GPT-5.5 |
| 安全、漏洞、注入、权限、合规、auth | security-review |
Claude Opus |
| 代码审查、review、pull request、代码质量 | code-review |
Claude Opus |
| 线上、故障、事故、日志、恢复、自愈 | self-healing |
MiniMax-M2.7 |
| 架构、技术选型、系统设计、跨模块 | architecture |
Claude Opus |
| 很长、长文档、第三方 API、视频、图像、多模态 | research |
Gemini-3-Pro |
| 前端、UI、组件、落地页、样式、beautiful | frontend |
Kimi K2.6 |
| 普通实现、写代码、开发、构建 | implementation |
DeepSeek-V4 |
Explain 输出
用 --explain 查看为什么选中某个模型：
node scripts/aios.mjs model-router route \
--task "用浏览器打开小红书发布页面，上传图片并填写标题" \
--profile balanced \
--explain
重点看这些字段：
profile：实际使用的策略，默认balanced。confidence：信号强度和胜出差距，低置信时可考虑拆任务或用premium。matchedSignals：命中的关键词和权重。why：人类可读解释。recommendedPhases：复合任务的分阶段建议；v2 只报告建议，不自动改写 team plan。
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.
- 3d ago First seen · 135 lines · 60 tokens per session scan A 5b24564fa988
model-router is a skill published in the GitHub repository rexleimo/aios (52 stars, last pushed 4d ago), licensed MIT. It adds 60 tokens to every session and 2,121 once invoked, about $0.0003 per session on Opus 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.
Other skills, from other repositories
bug-triage
Triage bugs reported in chat/issues, search for duplicates, file or update GitHub issues with full context, and push fix PRs.
ao-desktop-dev
Launch, restart, or troubleshoot the real AO Electron desktop app from this repository; run a checkout against isolated or real local AO data; combine PR branches for local UI review; and diagnose stale Electron processes, port conflicts, or preload bridge mismatches. Use whenever asked to run, open, show, or visually…
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.
agency-os
Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to…
orchestrate
Pipeline orchestration: dispatch the highest-priority ready tasks/work units to agents, manage capacity, and coordinate the Todo to Done flow. Invoked as /agiflow:orchestrate. Uses listtasks, listactivetasksbyorg, listmembers, updatetask, getworkunitprogress.
goal-flight
Portable Goal Flight workflow for long-running repo work: planning, dispatch, review, recovery, file-backed resume.