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.
git clone --depth 1 https://github.com/zhukunpenglinyutong/ai-maxWrote 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/commands/zhukunpenglinyutong/ai-max/auto)<a href="https://agentmods.dev/commands/zhukunpenglinyutong/ai-max/auto"><img src="https://agentmods.dev/badge/commands/zhukunpenglinyutong/ai-max/auto/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/commands/zhukunpenglinyutong/ai-max/auto"><img src="https://agentmods.dev/badge/commands/zhukunpenglinyutong/ai-max/auto.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00019 | $0.02107 |
| Opus 5 | $0.00010 | $0.01053 |
| Sonnet 5 | $0.00004 | $0.00421 |
| Haiku 4.5 | $0.00002 | $0.00211 |
Grade A, and why
auto 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 10d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auto 命令
根据用户输入自动选择最合适的命令执行。通过语义分析和关键词匹配，智能识别用户意图并路由到对应的专业命令。
核心理念
- 零配置: 用户无需记忆具体命令，描述需求即可
- 智能匹配: 基于优先级和语义权重进行最佳匹配
- 透明执行: 清晰展示选择逻辑，便于用户理解和调整
选择规则
优先级说明
- P0 (紧急): 阻塞性问题，必须立即处理
- P1 (高): 质量保障相关，影响代码可靠性
- P2 (中): 代码质量优化，提升可维护性
- P3 (低): 辅助性任务，改善开发体验
- P4 (默认): 通用开发任务，兜底选项
详细匹配规则
| 优先级 | 关键词 | 命令 | 适用场景 |
|---|---|---|---|
| P0 | 构建失败、build fail、类型错误、type error、编译错误、compile error、tsc 报错、npm run build 失败 | build-fix |
项目无法编译、TypeScript 类型检查失败、构建流程中断 |
| P1 | e2e、端到端、playwright、cypress、浏览器测试、用户流程测试、自动化测试、UI 测试 | e2e |
编写或运行端到端测试、验证用户交互流程、跨页面功能测试 |
| P1 | 覆盖率、coverage、测试报告、未覆盖代码、覆盖率不足、istanbul、jest coverage | test-coverage |
生成测试覆盖率报告、识别未测试代码、提升测试覆盖 |
| P1 | tdd、测试驱动、单元测试、unit test、先写测试、vitest、jest、测试优先 | tdd |
采用 TDD 方法开发新功能、编写单元测试、修复 bug 时补充测试 |
| P2 | 审查、review、检查代码、code review、代码质量、安全检查、漏洞、最佳实践 | code-review |
提交前代码审查、安全漏洞扫描、代码质量评估、最佳实践检查 |
| P3 | 清理、重构、refactor、删除未使用、dead code、优化结构、整理代码、抽取公共、消除重复 | refactor-clean |
移除死代码、优化代码结构、提取公共逻辑、消除重复代码 |
| P3 | 文档、docs、README、注释、API 文档、使用说明、更新文档、写文档 | update-docs |
更新项目文档、编写 README、生成 API 文档、补充代码注释 |
| P3 | 代码地图、codemap、架构图、模块关系、依赖分析、项目结构 | update-codemaps |
生成代码架构图、分析模块依赖、可视化项目结构 |
| P4 | 实现、开发、功能、feature、新增、添加、创建、修改、implement、develop（默认兜底） | plan |
新功能开发、现有功能修改、任何未匹配的开发任务 |
冲突处理规则
当用户输入匹配多个命令时：
- 优先级优先: 选择优先级数字更小的命令
- 精确优先: 完全匹配优于部分匹配
- 上下文优先: 根据用户历史操作推断意图
- 询问确认: 多个同优先级命令时，询问用户确认
执行步骤
1. 分析意图
- 对用户输入进行分词和语义解析
- 提取核心关键词和动作词
- 识别技术术语和上下文线索
2. 匹配命令
- 按优先级从高到低遍历规则表
- 计算每条规则的匹配分数
- 选择得分最高且优先级最高的命令
3. 显示结果
- 清晰展示选中的命令
- 说明选择原因和匹配的关键词
- 提供备选命令供用户参考
4. 执行命令
- 调用对应命令的完整流程
- 传递用户原始输入作为参数
- 保持执行过程的透明可见
输出格式
📊 智能命令选择
🎯 **已选择**: `/aimax:[命令]`
📝 **原因**: [详细的选择原因说明]
🔍 **关键词**: [匹配的关键词列表]
💡 **备选**: [其他可能相关的命令]
---
⏳ 正在执行 `/aimax:[命令]` ...
使用示例
示例 1: 新功能开发
用户：/aimax:auto 添加用户登录功能
📊 智能命令选择
🎯 **已选择**: `/aimax:plan`
📝 **原因**: 检测到新功能开发需求，需先制定实现计划确保架构合理
🔍 **关键词**: "添加"、"功能"、"登录"
💡 **备选**: `/aimax:tdd`（如果希望采用测试驱动开发）
---
⏳ 正在执行 `/aimax: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.
- 10d ago First seen · 190 lines · 19 tokens per session scan A 0383f6208860
auto is a command published in the GitHub repository zhukunpenglinyutong/ai-max (335 stars, last pushed 7mo ago), licensed MIT. It adds 19 tokens to every session and 2,107 once invoked, about $0.0001 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.