pisper: Instructions file for Codex

AGENTS.md

pisper AGENTS.md is an instructions file for Codex, OpenCode from ling-kong-ran/pisper. It costs 10,876 tokens per session, scanned A, original, MIT.

A set of project instructions for coding agents working in Pisper, an application that runs agents across desktop, terminal, and mobile interfaces.

In plain words
What is it for?
Use it when changing Pisper's React interface, Node runtime, Rust terminal client, desktop shell, translations, or agent data setup.
Why use it?
It gives agents the project's architecture, important directories, setup requirements, and data-safety rules so they can work in the right places.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is ling-kong-ran/pisper's own configuration. It tells Codex and OpenCode how to work on pisper itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pisper configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ling-kong-ran/pisper. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ling-kong-ran/pisper/release/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ling-kong-ran/pisper

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for pisper AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ling-kong-ran/pisper/agents-md/github.svg)](https://agentmods.dev/instructions/ling-kong-ran/pisper/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/ling-kong-ran/pisper/agents-md"><img src="https://agentmods.dev/badge/instructions/ling-kong-ran/pisper/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.

agentmods 80×15 button for pisper AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ling-kong-ran/pisper/agents-md"><img src="https://agentmods.dev/badge/instructions/ling-kong-ran/pisper/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 10,876 This file is loaded in full into every session.
When invoked 10,876 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.10876 $0.10876
Opus 5.5 $0.04350 $0.04350
Sonnet 5.5 $0.02175 $0.02175
Haiku 4.5 $0.01088 $0.01088

Measured 8d ago against content hash f29f807daffc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

pisper 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 8d 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.

AGENTS.md · 318 lines

How it starts

The opening of the file, as written. The whole thing — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

本文档用于指导在 Pisper 仓库中工作的开发者和 AI 代理。

项目概览

Pisper 是一个覆盖桌面端、终端和移动端的多代理应用,基于 Pi Coding Agent 构建。项目包含:

  • React Web 界面(开发服务器和生产静态资源)
  • Node.js 应用运行时与桌面伴随进程,承载会话、工具、MCP、技能、记忆、工作流、通道和计划任务
  • Tauri 2 桌面壳,包含系统 WebView 和 Node SEA 伴随进程
  • Rust Ratatui TUI 客户端

源码开发、验证与桌面 SEA 构建以 Node.js 24 为基线,补丁版本必须满足锁定依赖的要求。源码环境、npm 启动器所用宿主 Node 与移动端嵌入式 Node 的要求分别见 docs/development-workflow.md,不得从旧的 engines 声明推断完整 Runtime 支持范围。运行时代理数据默认保存在 ~/.pisper/agent,可通过 PISPER_AGENT_DIR 覆盖。不得提交该目录中的 API 密钥、机器人凭据或个人数据。

架构

路径 职责
src/ React + TypeScript 前端(Vite、Tailwind 4、shadcn/ui、Zustand、i18next)
src/app/ 应用壳:路由、Provider、i18n 接线和导航
src/features/ 功能页面(聊天、配置、技能、MCP/插件、工作流等)
src/components/ui/ shadcn/ui 基础组件;优先组合这些组件,避免编写一次性样式
src/components/app/ 应用级通用组合组件的推荐归属;按需要创建,不承载 Feature 业务规则
src/locales/{zh-CN,en-US}/ 翻译命名空间(namespace:key)
runtime/ Node 应用运行时(纯 ESM .mjs):HTTP API、代理集成、服务和工具
runtime/runtime/ Pi 代理运行时集成
runtime/services/ 领域服务(会话、MCP、计划任务、工作流、Provider 等)
runtime/tools/app/ 应用级代理工具(每个工具一个模块)
runtime/tests/ 当前统一的 Node 测试入口,涵盖 Runtime、前端纯逻辑、协议、构建与源码守卫
packages/pisper/ 私有源代码清单,以及发布为 pisper 的 npm 安装器/启动器
shared/ Runtime 与客户端共享的小型 JS 模块(例如工作流图和发布说明)
src-tauri/ Tauri 2 壳(桌面桥接、宠物窗口、更新器、CLI 安装)
src-tui/ Rust TUI(pisper CLI)
crates/ 独立 Rust 库、原生插件和平台适配模块
scripts/ SEA 打包、发布、冒烟测试和 i18n 检查脚本
docs/ 产品文档、截图、赞助配置和打包说明
dist/ Vite 生产构建输出
release/ 已打包的 SEA/TUI/Tauri 产物(已被 Git 忽略)

桌面端运行形态: Tauri 壳 → pisper-sidecar(Node SEA)→ sidecar-runtime/(Pisper Runtime、Pi 包、技能和原生模块)。开发 Web 流程中,runtime/index.mjs 嵌入 Vite 中间件,并默认在 127.0.0.1:5173 提供 SPA 和 API。

路径别名:@/* → src/*,@shared/* → shared/*。

规范执行方式

本文件同时服务于开发者和 AI 代理,规则分为三类:

  • 强制边界: 安全、协议兼容、发布流程,以及以“必须”“禁止”“不得”“只能”表述的要求。基础组件不依赖 Feature、跨 Feature 不访问内部实现、不得新增循环依赖均属于强制边界,不能仅凭变更说明豁免。
  • 默认建议: 以“默认”“优先”“建议”“可以”“应”表述的组织方式,例如子目录名称、组件共置和具名导出;其中同时含有明确禁止条件的部分仍属于强制边界。采用其他方案时,说明职责归属、依赖方向与取舍即可,不要求额外审批。
  • 迁移债务: 存量代码、工具与目标规范的已知偏差。新代码不得扩大偏差;本次涉及的区域优先治理,无法在当前范围完成的部分记录责任范围、迁移条件与验证方式,不要求顺带重写全仓库。

Read the full file on GitHub · 318 lines

Changes

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.

  1. 9d ago Changed · +4 lines · +707 tokens per session e24f327cceb6
  2. 24d ago Changed · +2 lines · +226 tokens per session f29f807daffc
  3. 25d ago Changed · +1 lines · +69 tokens per session 903c8d482a4c
  4. 1mo ago Changed · +128 lines · +5,626 tokens per session 723e8bb2d0f9
  5. 1mo ago Changed · +2 lines · +298 tokens per session 6ebcf850bc27
  6. 1mo ago Changed · +10 lines · +548 tokens per session 03976369b6a3
  7. 1mo ago Changed · +10 lines · +329 tokens per session 921c500ee027
  8. 1mo ago First seen · 165 lines · 3,780 tokens per session scan A aa666aff62ab

Subscribe to this mod's changes

pisper AGENTS.md is an instructions file published in the GitHub repository ling-kong-ran/pisper (297 stars, last pushed 3d ago), licensed MIT. It adds 10,876 tokens to every session, about $0.0435 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 2026-08-30.

Related

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).

microsoft/vscode · 9,649 tokens

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.

vercel/next.js · 7,549 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

denoland/deno · 3,077 tokens