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 instructions/beixiyo/ai-sync/agents-mdgit clone --depth 1 https://github.com/beixiyo/ai-syncWhat 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 | $0.02162 | $0.02162 |
| Opus 5 | $0.01081 | $0.01081 |
| Sonnet 5 | $0.00432 | $0.00432 |
| Haiku 4.5 | $0.00216 | $0.00216 |
Grade B, and why
ai-sync AGENTS.md scanned grade B with 1 finding 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.gemini/settings.json` How it starts
The opening of the file, as written. The whole thing — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent 指南 - ai-sync 项目
本文档为在 ai-sync 项目上工作的 AI Agent 提供必要信息。遵循这些指南以确保一致性和质量。
项目概览
ai-sync 是一个基于 TypeScript 的 CLI 工具，用于在不同 AI 工具（如 Cursor、Claude Code、OpenCode 等）之间迁移 AI 配置（Commands、Skills、Rules、MCP）
- 技术栈: TypeScript、Node.js (ESM)、pnpm、Vitest、ESLint (Antfu 配置)、tsup
- 核心逻辑: 位于
src/lib/，包含迁移器和转换器
文件结构
src/index.ts: CLI 入口点src/lib/configs/: 工具特定配置src/lib/converters/: 数据格式转换逻辑（例如 Markdown 到 TOML）src/lib/migrators/: 每个工具的高级迁移逻辑src/lib/utils/: 共享工具函数（文件 I/O、Logger 等）tests/: Vitest 测试套件
特殊说明
- 添加新工具支持时，更新
src/lib/configs/并实现必要的迁移器/转换器 - 参考
docs/sync-rules.md了解特定工具配置路径和转换逻辑 - 遵守
eslint.config.mjs设置，特别是forceTernary和docComment规则 - 如果在代码中发现
// @TODO或// FIXME，在任务范围内解决它们
CLI 交互规则
- 支持交互式选择和命令行参数两种模式
- 无参数时进入完全交互式选择
- 有参数时快速执行，跳过交互
- 工具选择支持多选，逗号分隔
- 支持 -s 指定源目录、-t 指定目标工具、-y 自动覆盖等参数
配置加载规则
- 自动查找家目录或指定目录中的 ai-sync.config.js 配置文件
- 支持 CommonJS 和 ESM 格式
- 支持 package.json 中的 ai-sync 字段配置
- 自定义配置与默认配置合并，自定义配置优先级更高
Rules 优先级规则
同步时按以下顺序优先选择规则源：
~.claude/{CLAUDE.md,AGENTS.md}
注意：不再向 Cursor 迁移 Rules，因为 Cursor 已支持自动检测
~/.claude/CLAUDE.md
Commands 转换总结对比
| 特性 | Gemini CLI | Cursor | Claude Code | CodeBuddy | OpenCode | Codex CLI |
|---|---|---|---|---|---|---|
| 文件格式 | TOML | Markdown | Markdown | Markdown | Markdown / JSON | TOML / YAML |
| 项目位置 | .gemini/commands/ |
.cursor/commands/ |
.claude/commands/ |
.codebuddy/commands/ |
.opencode/commands/ |
.codex/prompts/ |
| 全局位置 | ~/.gemini/commands |
~/.cursor/commands/ |
~/.claude/commands/ |
~/.codebuddy/commands/ |
~/.config/opencode/commands/ |
~/.codex/prompts/ |
| 参数语法 | {{args}} |
无特殊语法 | $ARGUMENTS, $1, $2 |
$ARGUMENTS, $1, $2 |
$ARGUMENTS, $1, $2 |
$ARGUMENTS, $1, $2, 命名参数 |
| Shell执行 | !{command} |
不支持 | !command`` (需声明 allowed-tools) |
!command`` (需声明 allowed-tools) |
!command`` (无需声明) |
配置文件白名单 |
| 文件引用 | @{filepath} |
不支持 | @filename |
@filename |
@filename |
@filename |
| 命名空间 | 子目录 | 子目录 | 子目录 | 子目录 | 子目录 | 子目录 |
| Frontmatter | 不支持 | 不支持 | 支持 | 支持 | 支持 | 支持 |
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.
- 2d ago First seen · 230 lines · 2,162 tokens per session scan B 8145cfd767c3
ai-sync AGENTS.md is an instructions file published in the GitHub repository beixiyo/ai-sync (9 stars, last pushed 27d ago), licensed MIT. It adds 2,162 tokens to every session, about $0.0108 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
claude-codex-settings CLAUDE.md
Claude Code instructions for fcakyon/claude-codex-settings, covering claude-settings, repo structure, cross-tool plugin format reference, plugin manifests and root marketplace files.
skills CLAUDE.md
Instructions for lovstudio/skills, covering claude.md, what this is, repo layout, how users install and skills.yaml schema.
cli-continues parsers.instructions.md
Instructions for yigitkonur/cli-continues, covering parser review guidelines, crash safety (critical), required exports, jsonl streaming and tool summarizer.
cli-continues security.instructions.md
Instructions for yigitkonur/cli-continues, covering security review guidelines — core utilities, command injection prevention (resume.ts), forward flag security (forward-flags.ts), handoff output safety (markdown.ts) and general.
cli-continues typescript.instructions.md
Instructions for yigitkonur/cli-continues, covering typescript review guidelines, type safety, discriminated unions, async patterns and import rules.
AgentHarbor CLAUDE.md
Instructions for abhiunix/AgentHarbor, covering claude.md, commands, architecture, two tauri windows and adapter trait — the core abstraction.