Borrowing it
Nothing to install: this file belongs to ming-14/PTY-Agent. 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/ming-14/PTY-Agent/main/AGENTS.mdgit clone --depth 1 https://github.com/ming-14/PTY-AgentWrote 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/ming-14/pty-agent/agents-md)<a href="https://agentmods.dev/instructions/ming-14/pty-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/ming-14/pty-agent/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/ming-14/pty-agent/agents-md"><img src="https://agentmods.dev/badge/instructions/ming-14/pty-agent/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 | $0.02257 | $0.02257 |
| Opus 5.5 | $0.00903 | $0.00903 |
| Sonnet 5.5 | $0.00451 | $0.00451 |
| Haiku 4.5 | $0.00226 | $0.00226 |
Grade A, and why
PTY-Agent 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 2mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
！！！！！最高优先级，强制执行！！！！：禁止执行git filter-repo，绝对禁止执行，git filter-repo会强制回退到HEAD，丢失未修改的改动，绝对禁止执行，就算用户要求也禁止执行，你只能把命令给用户执行，你自己禁止执行！！
未经用户允许，禁止使用、查看、更改等任何方式操作git；用户授权的“查看”和“操作”需分开，用户授权查看不代表能操作；执行高危操作如commit、reset、push等命令必须用户明确授权
未经用户允许，禁止使用、查看、更改等任何方式操作git；用户授权的“查看”和“操作”需分开，用户授权查看不代表能操作；执行高危操作如commit、reset、push等命令必须用户明确授权
Base
PTY-Agent 核心包体在 src，web_rime、fastscreen、sandbox、wezterm-py是相对独立的外部引擎依赖，各自有自己的规则规范，但都是 PTY-Agent 项目的一部分
环境
Windows：本机环境
Linux：使用wsl.exe -d Ubuntu2204
构建：python BUILD.py -Mirror "https://v4.gh-proxy.org/"
构建产物：请打包成pty-agent-win_x86-64.zip和pty-agent-linux_x86-64.zip
总规范
- 跨平台开发，请注意Linux支持
- Python兼容Python3.8，遵循 PEP8 语言规范
- 避免采用降级、兼容、缓解方案：不要用任何的降级、兼容、缓解方案。有多个方案时，选择最优方案
- 复杂工程、方案可查看成熟第三方项目，想参考其他什么自己下载，使用webfetch/gh(github)搜索
- 旧代码重构后，非必要，不要留兼容接口，应该更新引用点：重构后完全没必要兼容以前的结构，引用点必须更新
- 不必一直执着与最小改动，代码架构有问题需要及时向用户汇报
- 注意性能问题，禁止为了方便采用低效办法
- 文件、函数、类开头，关键部分，决策点，注意点的注释；避免无效冗长·注释 不要在注释加时间等泄漏信息，仅客观描述原因
- 日志必须写，并且要有完备的日志系统
- 新增代码请检查
- [] 关键部分注释加了吗
- [] 日志写了吗，是否符符合规范
- 请使用标准库、第三方库大量精简代码、手工实现复杂的，可下载库使用，需要什么库自行下载
- 例：计算字符宽度时，使用wcwidth，而不是手算
- 不要无用的防御编程与过度工程
- 例：
function A() {} if(type A === "function") A()错误
- 例：
- 提交git时，发现不是自己改动的文件时，请向用户询问是全部提交还是分多次提交，禁止静默只提交自身改动部分
- Bug 修复后，需撤销之前的无效修改点，不能让无效改动污染代码！
- Debug完成后，检查
- [] 旧改动删了吗
- [] 旧改动删了后，是否还能正常运行
- Debug完成后，检查
项目清洁度：不应出现在项目（代码，注释，文档等任何文件）中的内容
被ignore的文件不用理
历史痕迹（开发历程 / 时间 / 变更记录）
- 阶段标注："Phase N"、"Phase-N"（如 Phase 16、Phase-12）等
- 任务号："T7.11"、"T1.4"、"T-8.x"、"T64"、"T32"、"FR-8.x"等
- 日期："2021-01-01" 等任何日期
- 修复记录："已修复"、"修复为"、"曾"、"E4/D4/H-1/H-2/C-5 修复"、"黑盒报告"、"BUG-01"、"r4/r5"、"MEDIUM-x"等
- 旧字段/旧值说明："旧值 xxx 已删除"、"fs_mode/capabilities/path_rules 已移除"、"迁移指引"、"向后兼容"等
- 已删除文档的引用
- 开发脚本/实验引用："verify_low_flow.py"、"label_probe.py"、"setil_probe.py"、"lowil_test.py"、"实测定案"、"三路实验"、"对照 %TEMP%\opencode 实验结论"等
- 用户交互痕迹："用户拍板"、"已与用户对齐"、"用户决策"、"用户要求"等
- 旧组件/旧形态提及："sandbox.exe"、"AppContainer"、"IPC 形态"、"FileSystemIsolator"、"StatsCollectorImpl"等
- 其他项目提及："PTY-Agent"、"fastscreen"、"aichat"、"terminal_injector"、"opencode"（pyproject 包元数据除外）等
- 隐私内容，如用户名，env等
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.
- 2mo ago Changed · +2 lines · +61 tokens per session a42b8309fc63
- 2mo ago First seen · 124 lines · 2,196 tokens per session scan A 401a061e34cc
PTY-Agent AGENTS.md is an instructions file published in the GitHub repository ming-14/PTY-Agent (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,257 tokens to every session, about $0.0090 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.
PTY-Agent AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| PTY-Agent AGENTS.mdming-14/PTY-Agent | Instructions file | 2 | 1mo ago | MIT | A | 2,257 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |