empathize-with-others: Instructions file for Codex

AGENTS.md

empathize-with-others AGENTS.md is an instructions file for Codex, OpenCode from ZeroPointSix/empathize-with-others. It costs 768 tokens per session, scanned A, original, Apache-2.0.

A contributor guide for the Empathy AI Android project. It explains the four application modules, Windows and Unix build commands, release checks, Kotlin style rules, and testing locations.

In plain words
What is it for?
Use it when implementing features, running unit or device tests, checking formatting, preparing a release, or writing release notes.
Why use it?
It turns project-specific build, release, and coding expectations into instructions an agent can follow consistently.

Instructions file for CodexOpenCode

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

This is ZeroPointSix/empathize-with-others's own configuration. It tells Codex and OpenCode how to work on empathize-with-others 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 empathize-with-others configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ZeroPointSix/empathize-with-others. 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/ZeroPointSix/empathize-with-others/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/ZeroPointSix/empathize-with-others

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 empathize-with-others AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/zeropointsix/empathize-with-others/agents-md/github.svg)](https://agentmods.dev/instructions/zeropointsix/empathize-with-others/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/zeropointsix/empathize-with-others/agents-md"><img src="https://agentmods.dev/badge/instructions/zeropointsix/empathize-with-others/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 empathize-with-others AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/zeropointsix/empathize-with-others/agents-md"><img src="https://agentmods.dev/badge/instructions/zeropointsix/empathize-with-others/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 768 This file is loaded in full into every session.
When invoked 768 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 $0.00768 $0.00768
Opus 5.5 $0.00307 $0.00307
Sonnet 5.5 $0.00154 $0.00154
Haiku 4.5 $0.00077 $0.00077

Measured 2mo ago against content hash f51eae84e5c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

empathize-with-others 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.

AGENTS.md · 39 lines

What it actually says

Repository Guidelines

项目结构与模块组织

项目采用 Clean Architecture + MVVM,多模块拆分如下:domain/(纯 Kotlin 业务模型与 UseCase)、data/(Room/Retrofit 与仓库实现)、presentation/(Compose UI 与 ViewModel)、app/(应用入口与系统服务)。构建与版本管理在 build.gradle.kts、settings.gradle.kts、buildSrc/、config/ 中。资源与文档位于 assets/、文档/、Rules/。测试代码通常在 */src/test/ 与 */src/androidTest/。

构建、测试与开发命令

常用命令(Windows 示例):

.\gradlew assembleDebug
.\gradlew installDebug
.\gradlew test
.\gradlew :domain:test
.\gradlew :data:test
.\gradlew :presentation:test
.\gradlew connectedAndroidTest
.\gradlew lint
.\gradlew ktlintCheck
.\gradlew ktlintFormat

AI 请求日志可用 scripts\ai-debug.bat 与 scripts\ai-debug-full.bat。macOS/Linux 将 .\gradlew 替换为 ./gradlew。

发布流程与 Release 日志

每次发布必须满足以下要求:

  • Release 日志:发布前必须输出详细发布说明(新增功能、修复、重要变更/迁移、测试结果),并同步到 GitHub Release 页面。
  • 构建成功:必须完成 assembleRelease 且构建成功。
  • 安装验证:必须安装到设备并启动验证(设备不可用时需先告知并征询用户处理方式)。

编码风格与命名规范

遵循 Kotlin 官方规范,默认 4 空格缩进。类用 PascalCase,函数/变量用 camelCase,测试类以 *Test 结尾。状态管理使用 StateFlow + UiState,错误处理使用 Result<T>,ViewModel 使用 viewModelScope,禁止 GlobalScope。优先复用 presentation/ui/component/ 组件,Ios* 组件用于统一 iOS 风格。文档与沟通使用中文,代码注释使用英文。

测试指南

单元测试覆盖核心业务逻辑,位于 */src/test/;仪器测试在 */src/androidTest/,需连接设备。Room 迁移测试位置参考 app/src/androidTest-disabled/。运行单模块测试使用 :module:test,UI/设备测试使用 connectedAndroidTest。

提交与 PR 规范

提交信息采用约定式提交:feat:、fix:、docs:、chore:,可选作用域(如 fix(ci): ...),必要时在描述中带上需求/缺陷编号(如 PRD-00036)。PR 需包含变更说明、关联文档/Issue、测试结果与 UI 截图(若涉及界面)。开始任务前更新 WORKSPACE.md,记录当前任务与测试状态。

安全与配置提示

本项目为本地优先应用,API Key 与隐私数据仅存本机。配置 SDK 路径:复制 local.properties.example 为 local.properties。签名配置:复制 keystore.example.properties 为 key.properties,严禁提交真实密钥。

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. 2mo ago First seen · 39 lines · 768 tokens per session scan A f51eae84e5c9

Subscribe to this mod's changes

empathize-with-others AGENTS.md is an instructions file published in the GitHub repository ZeroPointSix/empathize-with-others (149 stars, last pushed 9mo ago), licensed Apache-2.0. It adds 768 tokens to every session, about $0.0031 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

empathize-with-others AGENTS.md compared with instructions from other repositories

empathize-with-others AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
empathize-with-others AGENTS.mdZeroPointSix/empathize-with-othersInstructions file1499mo agoApache-2.0A768Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode