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.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ccch1mneyyy/dsh-TUI --skill dsh-tui-guidegit 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/skills/ccch1mneyyy/dsh-tui/dsh-tui-guide)<a href="https://agentmods.dev/skills/ccch1mneyyy/dsh-tui/dsh-tui-guide"><img src="https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/dsh-tui-guide/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/skills/ccch1mneyyy/dsh-tui/dsh-tui-guide"><img src="https://agentmods.dev/badge/skills/ccch1mneyyy/dsh-tui/dsh-tui-guide.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 | $0.00041 | $0.00682 |
| Opus 5.5 | $0.00016 | $0.00273 |
| Sonnet 5.5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
dsh-tui-guide 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 today.
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.
What it actually says
dsh-tui 用户手册（索引）
用户手册全文就在本文件所在目录——skill 工具返回的 resourceBase。共 10 篇，
每篇中英各一份：中文文件名无后缀，英文加 .en.md。拿不到绝对路径时，用
glob 在 dsh-tui 包里搜 guide/dsh-tui-guide。
怎么用
- 跟用户同语言：中文提问读无后缀文件，英文提问读加后缀的那份；回答也用同一种语言。
- 先定位再读：20 个文件按主题分篇，整篇读既慢又挤上下文。先
grep关键词拿到命中行， 再用read带offset/limit只展开需要的那几段。 - 一次一到两篇：按下面的路由表挑最贴近的；跨主题时再补第二篇。
- 给出处：回答末尾写清来源（文件名 + 小节标题），用户能直接翻回去核对。
- 别编：手册没写的直说"手册没写"，再给保守建议；不要拿记忆里的旧行为顶替。
路由表
| 用户问的 | 文件 |
|---|---|
| 安装、首次启动、启动失败、排障 | getting-started.md |
| 日常使用、键位、斜杠命令、会话与工作流、设置 | user-guide.md |
| 输入框、鼠标、选中复制、粘贴、图片、问卷与审批 | interaction.md |
| 配置覆盖层、TUI 开关、agent preset、模型路由、MCP | configuration.md |
| Claude 后端：启用、登录、与 DSH 的差异、已知限制 | claude-backend.md |
| Codex 后端：安装、登录、渠道、Plan、会话与原生能力 | codex-backend.md |
| 主题、配色、自动检测、自定义主题 | themes.md |
| 从 Claude Code / Codex / OMP / zcode / Grok 迁移会话 | migrate.md |
| VS Code 集成、扩展、IDE 选区 | vscode.md |
| 插件生态、接缝稳定性分级 | plugins.md |
英文提问时把上表文件名接上后缀（例如 user-guide.en.md）。
除本文件外，这些副本由
scripts/build-guide.mjs从仓库docs/逐字节同步生成， 不要手改；改文档请改docs/再跑一次构建。
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- claude-backend.en.md 11 KB
- claude-backend.md 10 KB
- codex-backend.en.md 20 KB
- codex-backend.md 19 KB
- configuration.en.md 26 KB
- configuration.md 24 KB
- getting-started.en.md 15 KB
- getting-started.md 15 KB
- interaction.en.md 60 KB
- interaction.md 56 KB
- migrate.en.md 10 KB
- migrate.md 9.1 KB
- plugins.en.md 4.5 KB
- plugins.md 4.0 KB
- themes.en.md 9.5 KB
- themes.md 9.3 KB
- user-guide.en.md 60 KB
- user-guide.md 57 KB
- vscode.en.md 14 KB
- vscode.md 13 KB
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.
- today Changed · +1 lines acd6d5a4374c
- 3d ago Changed · +1 lines b7e8d4f84f05
- 8d ago First seen · 38 lines · 41 tokens per session scan A c0903f04c5ad
dsh-tui-guide is a skill published in the GitHub repository ccch1mneyyy/dsh-TUI (4,162 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 682 once invoked, about $0.0002 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 2026-09-30.
Other skills, from other repositories
submit-dsh-plugin
A submission checklist and workflow for adding a DeepSeek Harness plugin to the community’s public catalogue. It prepares the catalogue entry and checks the plugin’s repository, metadata, tests, and required files.
promentor
A tool that turns a software project into a hands-on course in the style of an MIT course. It can produce lessons, code walkthroughs, practical labs, behavior tests, grading, explanations, and AI reviews.
i-have-adhd
Apply adhd-friendly communication as a bounded agent workflow while preserving user intent, privacy, and host capabilities. Use when the user explicitly requests adhd-friendly communication behavior or files.
dsh-plugin-guide
Use when developing, reviewing, packaging, debugging, or answering questions about DeepSeek Harness (DSH) plugins — the plugin-based agent harness on vendored Cordis. Applies the official plugin-development constraints (plugin contract, cordis.yml layers, services/events/effects, tool DSL, bundles/profiles) backed by…
fatqat-workbench
A quantum-computing experiment guide that uses a local tool to simulate small circuits and physical hardware models. It covers superconducting devices, atom arrays, transmon leakage, and Rydberg-atom dynamics.
codex-sync
Operate dsh-codex-sync from this session — preview and import Codex chats, toggle Skills/MCP/import settings, check MCP mirror health, install the reverse MCP bridge.