DeepSeek-Harness-Desktop: Instructions file for Codex

AGENTS.md

DeepSeek-Harness-Desktop AGENTS.md is an instructions file for Codex, OpenCode from web-casa/DeepSeek-Harness-Desktop. It costs 2,781 tokens per session, scanned A, original, MIT.

A project instruction file for AI coding agents working on a desktop app built with Tauri, Rust, Node.js, and DeepSeek Harness. It records the app’s architecture, security rules, process handling, version sources, and message formats.

In plain words
What is it for?
Use it when modifying the desktop shell, embedded Harness runtime, installation links, process shutdown, security settings, or cross-component event contracts.
Why use it?
It gives agents the rules they must follow before changing the project. This helps prevent unsafe desktop behavior, mismatched versions, broken event handling, and incomplete updates.

Instructions file for CodexOpenCode

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

This is web-casa/DeepSeek-Harness-Desktop's own configuration. It tells Codex and OpenCode how to work on DeepSeek-Harness-Desktop 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 DeepSeek-Harness-Desktop configures →

Reuse

Borrowing it

Nothing to install: this file belongs to web-casa/DeepSeek-Harness-Desktop. 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/web-casa/DeepSeek-Harness-Desktop/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/web-casa/DeepSeek-Harness-Desktop

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 DeepSeek-Harness-Desktop AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/web-casa/deepseek-harness-desktop/agents-md.svg)](https://agentmods.dev/instructions/web-casa/deepseek-harness-desktop/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/web-casa/deepseek-harness-desktop/agents-md"><img src="https://agentmods.dev/badge/instructions/web-casa/deepseek-harness-desktop/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,781 This file is loaded in full into every session.
When invoked 2,781 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02781 $0.02781
Opus 5 $0.01391 $0.01391
Sonnet 5 $0.00556 $0.00556
Haiku 4.5 $0.00278 $0.00278

Measured 7d ago against content hash 49738a517fcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

DeepSeek-Harness-Desktop AGENTS.md scanned grade A 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 7d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

--profile、参数原样转发 pnpm、`spawnSync("pnpm", {shell: win32,
AGENTS.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — DSH Desktop

面向 AI 编码代理(codex/claude 等)的项目上下文基线。先读本文,再读 README.md。

项目本质

Tauri 2 壳 + Rust dsh-sidecar 监督器 + 内置 Node 24 运行官方 DeepSeek Harness(@deepseek-ai/dsh不 fork,pin 版本)。桌面层只做生命周期: Tauri 管窗口/托盘,sidecar 管 Harness 进程树,Harness Web UI 原样加载。

不可违背的安全不变量

  • harness 窗口 capability 为空集;远程 webview 零 IPC 面,且导航只允许 就绪时捕获的 origin(same_origin,见 harness/mod.rs)。
  • 桌面命令经 app ACL(src-tauri/build.rs AppManifest)只授权 bootstrap。
  • 外部 deep link(dsharness://plugin/install)只产生「待确认安装请求」, 绝不静默安装;协议/包名/来源在 Rust 侧全量重校验后才可进入 UI。
  • DSH_HOME 0700、拒绝符号链接;withGlobalTauri: false + CSP。
  • 进程树保证:unix 进程组 + sigaction;Windows Job Object + 隐藏控制台 CTRL_C 优雅关闭(platform.rs)。任何改动不得弱化。
  • 零符号链接不变量限定范围src-tauri/resources/runtime/harness 与安装包内 runtime/harness 子树必须完全物化(materialize.ts + check-runtime-links.ts 断言)。macOS .app 框架自身的系统级链接不在其列。
  • NDJSON 协议契约与 golden 测试(ndjson_golden_events)同改:改事件结构 必须同时更新 sidecar、Tauri apply_state_eventverify-runtime.ts 三端。

版本单一事实源(改动版本时必须同时改全部)

文件 内容
runtime/runtime-manifest.json desktop/harness/node/sidecar 版本 + nodeSha256(6 平台)
package.json(根) desktop 版本
src-tauri/Cargo.toml / tauri.conf.json desktop 版本 + dsh-sidecar 依赖的 version pin(与 crates/dsh-sidecar 同步;cargo-deny wildcards=deny 要求非空版本)
crates/dsh-sidecar/Cargo.toml sidecar 版本
runtime/package.json + package-lock.json harness pin(npm install 刷新锁)
.nvmrc CI 脚本 Node(== manifest.nodeVersion)
snap/snapcraft.yaml Snap Store 包版本(== desktopVersion)

scripts/lib/node-distribution.ts 是由 manifest 生成的下载路径白名单,不是第二 个版本事实源;Node bump 时执行 pnpm runtime:node:generate 并提交结果。 release:preflight 会拒绝未同步的生成文件。

Snap 包只能由同一原生 job 从当前 checkout 生成的、已过 verify-bundle --bundle deb 的本地 DEB 输入;不得下载/重包装 GitHub Release 资产。snap/bin/launch-dsh-desktop 必须无条件将 DSH_HOME 与 XDG 数据目录 固定到 $SNAP_USER_COMMON,并清除 DSH_RUNTIME_DIR;不得为方便调试放开 classicdevmodehomeremovable-media

Snap 的 part source 必须是当前 checkout 内的本地输入;不得重新引入会在构建期拉取 可变 Git 分支的 extensions: [gnome]。GNOME/WebKit/GPU 运行期集成使用经过定义 复核的本地 command-chain relay 与 Store 签名的 gnome-46-2404 / mesa-2404 content provider;变更它们须同时更新 scripts/lib/snap.ts、定义测试与最终包 verifier。

Read the full file on GitHub · 156 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. 7d ago First seen · 156 lines · 2,781 tokens per session scan A 49738a517fcb

Subscribe to this mod's changes

DeepSeek-Harness-Desktop AGENTS.md is an instructions file published in the GitHub repository web-casa/DeepSeek-Harness-Desktop (117 stars, last pushed 2d ago), licensed MIT. It adds 2,781 tokens to every session, about $0.0139 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). 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

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,182 tokens

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 · 6,785 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 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 · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens