Borrowing it
Nothing to install: this file belongs to wlyaaaaa/ai-cli-profile-manager. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/wlyaaaaa/ai-cli-profile-manager/main/AGENTS.mdgit clone --depth 1 https://github.com/wlyaaaaa/ai-cli-profile-managerWrote 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/instructions/wlyaaaaa/ai-cli-profile-manager/agents-md)<a href="https://agentmods.dev/instructions/wlyaaaaa/ai-cli-profile-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/wlyaaaaa/ai-cli-profile-manager/agents-md/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/instructions/wlyaaaaa/ai-cli-profile-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/wlyaaaaa/ai-cli-profile-manager/agents-md.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 | $0.01302 | $0.01302 |
| Opus 5.5 | $0.00521 | $0.00521 |
| Sonnet 5.5 | $0.00260 | $0.00260 |
| Haiku 4.5 | $0.00130 | $0.00130 |
Grade A, and why
ai-cli-profile-manager AGENTS.md 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 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.
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 — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AICLI 项目规则
范围与事实源
- 只支持 Windows 11 x64、PowerShell 7；保留原生 Codex、Claude Code、Qwen Code、OpenCode 与官方 Rust Open Interpreter 的交互，不做另一套 GUI、PTY、Agent 或通用聊天历史库，不汉化上游本体。
- Provider 差异放数据 Manifest 和适配器，品牌集中定义。型号、窗口、档位和启用集合查
data/providers、data/model-catalogs、data/local-model-set.json，不把旧验收记录当现行身份。 - 维护契约保留跨模块合同和本人已定取舍；machine run说明机器运行入口。研究输入和历史回执不是当前能力证明。
- 用户首页保持五项简短说明。两本完整手册及 PDF 目前是打包、帮助与测试的依赖，保留源文/PDF哈希一致；不再把贡献指南、过程记录复制成另一套规则。
不可偷换的产品行为
- Codex harness 所有当前和未来模型统一用原生
danger-full-access，不按厂商降权；交互式start的权限交给上游。默认注册public_web_search，保留--no-web-search；关闭搜索不改变权限。搜索只用固定 HTTPS RSS provider，不允许任意地址、重定向、凭据或公开查询正文。 - 持久恢复仅用 app-server
thread/resume继续同一个真实 thread/session，并核对 workspace、Profile 指纹、实际 model/provider、requested/effective effort 和权限；新会话、身份漂移、重放或损坏证据不能冒充恢复。恢复账本只存必要身份、游标与哈希，不存正文、隐藏推理或工具载荷。 - 云端 Codex 只开放上游真实支持的 Responses，不能把 Chat Completions 或另一家 Agent 接口改名冒充。exact 预设保留其模型、套餐和端点，不自动 fallback、不改绑退役 ID；厂商默认别名本身跟随最新版本时（如
deepseek-flash）保持用默认别名，不钉日期版本；同厂商显式 --model 或自定义 Profile 可以换模型，模型目录不是凭据白名单。 - 原生 ChatGPT/Codex 和官方 Claude 是连续性基准，不附加第三方目录或压缩策略。AICLI 接入的非 OpenAI Codex 在真实最大上下文 90% 自动压缩；本地窗口保持 262144。未知 Claude 模型不猜容量，并清除继承的压缩/窗口变量。
aicli.third-party-continuity.v1：有损压缩前写项目既有状态，恢复后重读规则、状态和 diff；不建立第二事实源，不关闭溢出保护。- 本地模型按需使用，不代替原生委派策略。日常增减只走
scripts/Sync-LocalModelConfiguration.ps1，保留各引擎专有参数；普通同步做必要读回，实际故障再定向验证，不机械要求全客户端实跑。 - 菜单、默认项和启动提示显示真实模型名称，不出现 main、local-default、主用/复核等内部别名。兼容入口去重仍记住实际选中的稳定 ID，不暗中重路由。
- Desktop 桥沿用官方动态模型目录及官方引擎发现，未知通知和请求透传；不靠固定版本白名单阻止官方升级。机器安装、已加载进程和用户验收分别核实。
配置、恢复与验证
- 不永久写全局 Provider 变量，不覆盖用户基础 config/settings 或官方登录；只在真实 CODEX_HOME 维护身份可验证的派生配置，保留未知或用户改过的文件。
- 需要 Key 的 Profile 一律用 passwordcenter:厂商 引用密码中心已登记且带 native_hosts 的厂商，不创建 DPAPI 副本；旧本地密文只在迁移期兼容读取，用 Invoke-AiCliSecretMigration 迁移引用。运行时凭据值只进入一次性管道或必要客户端子进程，不进入参数、Git、日志、异常或新生成的启动脚本。eject 将已有本机配置按字节原样复制到选定目录，生成脚本保留密码中心引用或运行时输入。普通端点与工作区 ID 原样显示；真实凭据仍须过滤输出。Open Interpreter 允许显式传入上游支持的权限参数，保留不存在或冲突参数检查。禁止字符串执行用户参数。自定义远端明文 HTTP 默认拒绝。
- 普通卸载保留上游 CLI、登录、本地模型、Profile 和秘密；彻底清理另列准确范围。删除本地 OAuth 文件不代表远端撤销；模块更新不顺手替换独立登记的 Desktop 桥。
- Windows 路径用 Known Folders；中文 PowerShell 脚本用 UTF-8 BOM，Markdown/JSON 用 UTF-8 无 BOM。
- 离线验证：
pwsh -File scripts/Test-Release.ps1、Pester 5.5+ 的Invoke-Pester -Path tests；发行再跑scripts/Build.ps1。覆盖参数、中文路径、隔离、原子写入、端口竞争和恢复。 - CI 不读取真实 Key，不跑付费 Live。Live Tool Test 仅开放隔离 nonce 工具，隔离不能证明就报告限制；未完成当期真实验证不能标 Provider 可用。两本 PDF 变动时由
scripts/Build-Pdfs.py生成并验版，源文哈希必须匹配。
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 Changed · +128 tokens per session ed0067bca727
- 1mo ago Changed · -1 lines · -50 tokens per session 215a51b108dd
- 1mo ago Changed · -25 lines · -1,281 tokens per session 4014efe4c070
- 1mo ago Changed · +1 lines · +321 tokens per session 96d4a9dc21b1
- 1mo ago Changed · +142 tokens per session e28e7027ea32
- 1mo ago Changed · +2 lines · +312 tokens per session 3233d7d7ab13
- 2mo ago First seen · 52 lines · 1,730 tokens per session scan A ccbd8006f3c6
ai-cli-profile-manager AGENTS.md is an instructions file published in the GitHub repository wlyaaaaa/ai-cli-profile-manager (1 stars, last pushed 2d ago), licensed MIT. It adds 1,302 tokens to every session, about $0.0052 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.