dsh-TUI is a terminal interface plugin for DeepSeek Harness that gives the coding agent a Claude Code-style display with live status, streaming thoughts, rollback, context usage, and TPS information. It is for users who prefer a richer terminal workflow, and the catalogue entries extend the DeepSeek Harness environment with related skills and instructions.
Borrowing it
Nothing to install: this file belongs to ccch1mneyyy/dsh-TUI. 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/ccch1mneyyy/dsh-TUI/main/AGENTS.mdgit clone --depth 1 https://github.com/ccch1mneyyy/dsh-TUIWrote 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/ccch1mneyyy/dsh-tui/agents-md)<a href="https://agentmods.dev/instructions/ccch1mneyyy/dsh-tui/agents-md"><img src="https://agentmods.dev/badge/instructions/ccch1mneyyy/dsh-tui/agents-md.svg" alt="Measured on agentmods" 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 | $0.02093 | $0.02093 |
| Opus 5 | $0.01046 | $0.01046 |
| Sonnet 5 | $0.00419 | $0.00419 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
dsh-TUI 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 6d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
dsh-TUI 是 DeepSeek Harness 的终端界面插件：零核心改动、纯插件挂载的 Claude Code 风格 TUI（@deepseek-harness-tui/dsh-tui）。Agent、会话、模型、工具、持久化与策略域由 DeepSeek Harness 拥有，本包只消费它们。改动前先读 docs/contributing.md（本仓库共享开发契约的权威文本）与 ADAPTER.md（上游边界与契约）；整体结构见 docs/architecture.md。
仓库布局
src/index.ts 公共 Cordis 插件入口、配置 Schema、对运行时实现的惰性移交
src/plugin.ts 运行时实现：TTY 校验、服务注册、Agent 创建/恢复、React 树挂载与收尾
src/channel.ts 会话事件 → 视图投影 + 非 React 动作面（submit/steer/rewind/resume/切换）
src/screens/ Chat.tsx 交互协调器与状态栏呈现
src/components/ 功能组件；design-system/ 是主题感知原语
src/themeCatalog.ts 内置、静态 JSON 与运行时插件主题的统一列表/解析
src/ui.ts 本地渲染器、主题化 Box/Text 与公共 TUI 原语的首选门面
src/ink/ 移植的 Ink 渲染器与终端实现——敏感基础设施，改动聚焦并附专用回归
src/native-ts/ 渲染器使用的移植 Yoga 布局引擎
src/cc/ Claude Code 风格的终端格式化与呈现辅助
src/dsh-adapter/ 唯一允许 import 官方 @deepseek-ai/* 的位置；themes.ts 提供 tuiThemes 插件接缝
src/*Prefs.ts 等 ~/.dsh-tui 下的持久化用户偏好与会话元数据
.agents/skills/ 仅供仓库维护者使用的项目技能，不随 npm 包分发
presets/ 随包分发的 preset（liangshen）
bin/dsh-tui.js dsh-tui 直达命令入口
vendor/dsh-std vendored 依赖（frozen lockfile 构建，见 scripts/build 相关脚本）
dsh-ecosystem-spec/ 生态适配规范子项目（自带 CONTRIBUTING 与治理文档）
cordis.patch.yml profile 安装的包级覆盖层；行序、行 ID 与 insert/override 语义关键
cordis.yml 直接 Cordis/DSH 启动的完整裸组合示例
scripts/ 无头回归、复现环境、探针与诊断；运行前先读脚本头部说明
docs/ 根 README 之外的完整文档；中文无后缀，英文 .en.md 后缀
lib/ 由 src/ 生成的产物——忽略入库、随 npm 分发，绝不手改
完整仓库地图与运行时链路见 docs/contributing.md。
命令
pnpm install --frozen-lockfile # pnpm 11；Node ^22.19 || >=24（CI 用 Node 24）
pnpm compile # 干净编译 src/ → lib/types/（先删整个 lib/）
pnpm build # compile + 全部构建门禁
pnpm verify:build # 构建门禁（边界/契约/patch surface/plugin 系列等），不重复编译
pnpm verify:package # npm tarball 目标完整 + 入口 smoke import
pnpm smoke # 通用无头屏幕组装冒烟
仓库没有根级 test 或 lint 脚本——不要声称跑过它们。静态关口是 TypeScript 构建；行为验证靠聚焦回归脚本与复现环境。多数用普通 node 调用的脚本 import lib/types/，先 pnpm build；import TypeScript 源的脚本在头部声明 node --import tsx/esm <script>。不要凭扩展名推断输入层（verify-themes.mjs 实际经 tsx import src/）。scripts/ 还含取证/交互工具（堆分析、PTY 探针、回放捕获、性能探针），不是有界测试，不要当套件全跑。
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.
- 6d ago First seen · 73 lines · 2,093 tokens per session scan A 392d986325ef
dsh-TUI AGENTS.md is an instructions file published in the GitHub repository ccch1mneyyy/dsh-TUI (2,850 stars, last pushed today), licensed MIT. It adds 2,093 tokens to every session, about $0.0105 per session on Opus 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.
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.
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.
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).
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).
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.
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.