system-prompt 35

DSH 图形化 Agent 配置台：可视化拼装提示词、工具、技能、子代理与备用模型，按预设绑定即接管；自建预设走平台的预设注册入口，所有配置存在插件自己的数据里，卸载即恢复原状。

Lazy senior dev mode for DeepSeek Harness: always-on minimal-code ruleset, intensity switching, and short review/audit/debt/gain/help skills

DeepSeek Harness 默认 System Prompt 管理插件：在 Web GUI「设置」里浏览、检索并覆盖最终装配进每轮会话的系统提示词。

DeepSeek Harness 的 soul.md 风格人设 + 长期记忆插件：设置页输入人设卡名称和内容即可，文件由插件自动管理；可按工作区指定人设、聊天框可给会话单独切人设；AI 可自行演化人设与记忆（soul_read/soul_update/memory_*）。

Edit a DeepSeek Harness (dsh) custom mode: system prompt, base mode, and plugin switches.

为 DeepSeek Harness 添加个性化设置。

Tacit learns what you leave unsaid in your prompts — from messy turns and your own corrections, with zero clicks — and tells the agent how to compensate, on every turn, via a system-prompt section you can read and edit.

Persona engine for AI coding harnesses (DeepSeek Harness; the ZCode adapter is retired as of 2026-09-19 and kept for history only): self-name per model, self-image (appearance) and reply tone per model (both opt-in), user address, stance, character, per-i

Model policy for DeepSeek Harness (DSH): set_model / list_models agent tools, preset mode with switch_preset / list_presets, a configurable stage-to-model system prompt, plan-mode auto-transition, provider whitelist and context-window guards, active-model

会话注入门控：给 DeepSeek Harness (dsh) 加一个会话级上下文裁剪闸门，按会话取消/恢复插件贡献的 skill、tool、系统提示词段落——3 条影子通道、5 条本地路由、零依赖零配置。Per-session injection gate for DeepSeek Harness (dsh): trim skills, tools and prompt sections per session. Zero-config, zero dependencies.

Chinese-thinking system-prompt section for DeepSeek Harness: make your dsh agent think and answer in simplified Chinese (code/commands stay verbatim).

Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent tu

把 git 状态与仓库规范动态注入 system prompt：分支/脏文件数/最近提交 + 仓库规范指引（官方 system-prompt section/context/variable 缝隙插件）

DSH 提示词工作台：看清 system prompt 的每一段、写下你自己的家规、体检重复与矛盾，并记下每次改动。

Make the model believe it is inside the Z.ai Code (Zhipu ZCode) agent environment: replaces the harness identity opener and injects a ZCode rules skeleton with a dynamic project section. 让模型认为自己处于智谱 ZCode Agent 环境。

给 DeepSeek Harness 用的个人提示词管理器：把「个人提示词 + 系统提示词改动」存成预设，按会话或全局挂载，并能改写、关闭、还原 DSH 的原生段落，还能看清模型实际收到的最终提示词。

驯兽师（驯兽场）：把人类语言翻译给智能体的 DSH 插件——注入「开智」内核（第一性原理 + 需求剖析 + 极简沟通 + 最少 token），左上角悬浮萌宠，设置页可配内核与开关。

View and edit the current session's system prompt (in-memory, session-local override) for the DeepSeek Harness

Fork of @deepseek-ai/dsh-agent-instructions that delivers the workspace instruction baseline as system-prompt sections, keeping the upstream mid-session reminder path.

DeepSeek Harness 插件：把一段自定义 Markdown 提示词注入每次模型请求（独立上下文注入行），可在设置页编辑，并支持从 Claude Code / Codex 一键导入规则。

Third-party DeepSeek Harness plugin: per-workspace custom prompt configured from a slash command and injected into the model context at session start.

在会话工具条挂按钮，点击后开新标签页管理提示词；点【注入】可在当前会话下一次模型 step 前注入 prompt 到 system prompt。

User-only instruction memory for DSH: long-term instructions maintained in the settings UI and auto-injected into every conversation — the model has no write access. 指令记忆：只由用户在设置页维护的长期指令，自动注入此后每轮对话；模型没有任何写入口。

Standing system-prompt rule keywords that steer agent behavior mid-session via notice injection. 常驻系统提示规则关键词（notice 注入引导行为）

Repository prompt plugin with a live top-bar enable/disable switch (framework edition: ships a neutral placeholder directive).

Deterministic system-prompt section ordering for DeepSeek Harness — fixes KV-cache invalidation from unstable same-order section ordering across session resume. / 确定性 system-prompt section 排序：修复会话恢复时同 order section 排序漂移导致的 KV 缓存断层。

Read what an agent preset contributes to the prompt from the DeepSeek Harness settings UI: the persona prefix, suffix, complete mode and runtime-context toggle the preset composes with, and the named prompt sections it registers in its own name

DeepSeek Harness plugin: Set AI Language via system prompt injection

DeepSeek Harness 的三合一能力台：提示词定制（按名称屏蔽 / 替换 / 注入 / 排序，按会话阶段与 agent 预设分层）+ 技能集合管理（导入 / 分组 / 开关）+ MCP Server 接入（分层遮蔽与工具级启停）。纯插件注入，不动官方源码。

给 DeepSeek Harness 用的个人提示词管理器：把「个人提示词 + 系统提示词改动」存成预设，按会话或全局挂载，并能改写、关闭、还原 DSH 的原生段落，还能看清模型实际收到的最终提示词。

给当前 DSH 的全部会话与子代理统一附加一段额外说明和上下文：设置页分段维护、实时预览、热生效。

cc-switch-style global prompt for DeepSeek Harness (dsh 0.1.5): one user-editable block injected into the system prompt of every conversation, mirrored into each session project's AGENTS.md, and naming the harness's user-global AGENTS.md by absolute path

Agent-mode floating window for DeepSeek Harness (dsh): switch a session's system prompt between the harness's own prompt and 13 archived coding-agent CLI prompts (Claude Code, Codex CLI, Antigravity, Grok, Kimi, MiniMax, opencode, Pi…) from a draggable We

Forces periodic Engram memory recall and save reminders for DeepSeek Harness agents: injects a dynamic system-prompt context that reminds the model to load prior session memory at the start of a session, and to save new decisions/bugfixes/learnings every

Inject an extra system-prompt section into a DeepSeek Harness agent, shipped as a configurable bundle.